dashpivot_get_actions
ChatGPTLists Dashpivot actions from the actions register: what is open, overdue, or assigned to someone. When to Use - "What actions are open / overdue?" → call with no arguments. - "What is assigned to me?" → { assignedToMe: true } - "Show me the top 10 actions across my workspace" → { pageSize: 10 } - "What actions are open in this project?" → { _path: ["/ws_xxx/p_xxx"] } - For the actions linked from a specific form ("what actions came out of this inspection?"), use dashpivot_get_forms instead: each Actions field there already carries status, assignee and due date. Defaults No arguments returns open actions across every workspace you can access, overdue first (earliest due date first, undated last), 25 per page. An action is open until it reaches its template's final workflow column. Who Sees What Matches the web app. A workspace member sees the whole register. A project member sees actions raised from forms in that project and its teams; a team member sees actions raised from forms in that team. Without _path you also see actions assigned to you and actions you created directly in the register. Parameters (all optional) - _path: workspace, project or team paths from dashpivot_get_workspace_structure. Narrows to that folder exactly like its register on web. You can only pass folders you have access to. - status: "open" (default), "closed", "all", or workflow column titles listed in availableStatuses. - overdue: true for open actions past their due date. - dueBefore / dueAfter: ISO 8601 due-date bounds (inclusive). - assignedToMe: true for actions assigned to you. - assigneeIds: Sitemate user ids (sitemateUserId from dashpivot_get_users, or assignees[].id from a previous response). - pageSize / pageCursor: pagination; pass pageDetails.cursor as pageCursor for the next page. Response results[] holds one record per action: name, url (opens it in the web actions register; cite it), status and workflowColumn, isOpen, isOverdue, dueDate, assignees ({ id, name? }; name is absent when unresolved, never show the id as a name), source (form, project, team it was raised from), fields[] (description and completion notes under their template labels), createdAt, updatedAt. Each page also returns totalActionCount, availableStatuses and instructions. When results come from several regions, they are ordered within each region. - A top-level results (Copilot clients only) is a { url, title } citation list for client rendering — read action data from data.results, not here. Examples - Open actions: {} - Overdue in a project: { _path: ["/ws_xxx/p_xxx"], overdue: true } - Everything assigned to me, including closed: { assignedToMe: true, status: ["all"] } - Due this month: { dueAfter: "2026-10-01T00:00:00Z", dueBefore: "2026-10-31T23:59:59Z" } <!-- mcp-router:region-aware-pagination --> Pagination across regions: The response includes pageDetails.regions keyed by region (e.g. au1, uk1). To get the next page, pass pageCursor as a JSON object (not a string) with an entry for each region where isLastPage: false. Example: pageCursor: {"au1": "ws_abc", "uk1": "ws_xyz"}. Omit pageCursor entirely for the first page. pageSize applies per-region — the response may include up to pageSize × N items where N is the number of regions with data.
dashpivot_get_forms
ChatGPTRetrieves form data (filled-in records) for summarization, analysis, and reporting. When to Use - If the user provides a specific _path, call dashpivot_get_forms directly — do NOT call dashpivot_get_workspace_structure or dashpivot_get_templates first. - If the user asks about forms without a path, follow the standard discovery workflow. - If dashpivot_get_forms returns 0 results, check the instructions field for diagnostic guidance before making follow-up calls. - Actions fields on returned forms are enriched inline with each linked action's status, assignee and due date. For open, overdue or assigned-to-me questions that do not start from a form, call dashpivot_get_actions instead. Required Parameter - _path: Array of FlakeID paths (max 100). Use _path values from dashpivot_get_templates or dashpivot_get_workspace_structure (e.g., ["/ws_xxx/p_xxx/app_xxx"] or ["/ws_xxx"]). Key Parameters - formName / fieldFilters: Filter forms - workflowStep: Filter by workflow column — accepts position numbers (1, 2) and/or column name strings ("Supervisor Approval"). Case-insensitive. - createdDate: Filter by creation date range ({ after?, before? } — ISO 8601 strings in UTC, e.g. 2026-01-01T00:00:00Z). Use when the user is asking about when forms were started or opened. - updatedDate: Filter by last-updated date range ({ after?, before? } — ISO 8601 strings in UTC, e.g. 2026-01-01T00:00:00Z). Use when the user is asking about when forms were submitted, completed, or finalised — updatedAt advances when a draft is filled in or saved, while createdAt is fixed at the moment the form was first opened. - fieldIds: Return only specific fields (use IDs from dashpivot_get_templates) - includeArchived: Defaults to false (active forms only) — leave this unset for ordinary questions like "how many forms are there". Only set true when the user explicitly asks about archived, historical, or "all" forms regardless of status; totalFormCount will then include archived forms too. - pageSize (default 10, max 10), pageCursor for pagination Choosing createdDate vs updatedDate A form can be drafted on day 1 and submitted on day 8. createdAt is fixed at draft time; updatedAt reflects the last save. Map customer phrasing to the right filter: - "submitted / completed / filled out / finalised in the last week" → updatedDate - "started / drafted / opened / created in the last week" → createdDate - Both filters can be combined; they compose with AND. - When the intent is ambiguous, prefer updatedDate and state the choice in your reply. - All date bounds are interpreted as UTC. Convert any relative or local-time phrasing ("today", "last week") to absolute UTC ISO 8601 strings before calling. Response Format (compact) Compressed JSON with ~63% fewer tokens. Field values are lossless. Forms are grouped by app. Structure: - apps: array of app groups, each containing: - appPath: shared app path for this group - fields: array of { name, kind } — field definitions declared once per app - forms: array of { id, name, num, workflowCol, created, by, state, values } — each form's values array is positionally mapped to fields - results (Copilot clients only): one { url, title } per form, for client citation rendering — read form data from apps, not here - Shortened keys: id=itemId, num=automatedFormNumber, workflowCol.pos=workflowColumn.position, workflowCol.name=workflowColumn.name, created=createdAt, by=createdBy.name - state (e.g., "active", "archived") is present per form when includeArchived is true, so you can tell which forms in a mixed result are archived - Pagination: pass pageDetails.cursor back as pageCursor to fetch the next page. pageDetails.pageNumber is informational only. Example response: ``` {"apps":[{"appPath":"/ws_xxx/p_xxx/app_xxx","fields":[{"name":"Inspector","kind":"singleLineInput"},{"name":"Status","kind":"category"}],"forms":[{"id":"form_xxx","name":"Inspection #1","num":"SI-001","workflowCol":{"pos":2,"name":"Supervisor Approval"},"created":"2026-03-20T10:…
dashpivot_get_lists
ChatGPTRetrieves Dashpivot lists (spreadsheet-like data containers): columns, items, and property values. Lists power list fields and list property columns in forms — use this to understand what data populates form dropdowns and lookup fields. Modes (dispatched by leaf prefix of each _path) - Browse (leaf is ws_ or p_): returns list metadata plus columns (so the LLM can see what each list is shaped like and read columns[].id for follow-up columnFilters). items and itemsPagination are omitted. Use when discovering which lists exist under a workspace/project. - Details (leaf is li_): returns full data for the named list — columns, items, and property values. Use when a specific list has been identified to inspect. columns is always present on every list entry (empty array when the list has no columns). Browse and details paths can be mixed in one call — each entry resolves on its own leaf prefix. When to Use - If the user provides a specific _path, call dashpivot_get_lists directly — do NOT call dashpivot_get_workspace_structure first. - If the user asks about lists without a path, follow the standard discovery workflow: browse first, then narrow to a li_ path for details. - If dashpivot_get_lists returns 0 results, check the instructions field for diagnostic guidance. Required Parameter - _path: Array of FlakeID paths (max 100). Workspace/project paths (e.g., ["/ws_xxx"], ["/ws_xxx/p_xxx"]) trigger browse mode; list paths (e.g., ["/ws_xxx/li_xxx"]) trigger details mode. Key Parameters - listName: Filter by list name (case-insensitive partial match) — narrows which lists are returned in browse mode. - itemValue: Filter items by display value — the Item column shown in the list library (case-insensitive partial match). Only meaningful in details mode. - columnFilters: Filter items by column values. AND across entries, OR within each entry's queries. Each filter has a columnId (lp_ FlakeID — read from columns[].id in a prior details response), queries (array of one or more string/number values for OR matching within the entry), and an optional match mode controlling how each query compares to the cell value: "contains" (default — case-insensitive substring), "exact" (case-insensitive equality — use for IDs, codes, and precise numeric matches: queries: ["1"] with match: "exact" matches "1" only, NOT "10" or "9991"), or "prefix" (case-insensitive starts-with). To find rows where a column is empty / has no value, fetch the list without columnFilters and look for null in each item's positional properties array at the relevant column index. Only items matching ALL filter entries are returned. Only meaningful in details mode. - pageSize (default 25, max 25), pageCursor for list-level pagination. - itemPageSize (default 100, max 1000) — items per details list per page. Silently ignored for browse paths. - itemCursors — per-list item pagination cursors keyed by full list path (e.g. { "/ws_xxx/li_yyy": "lr_..." }). Each value is an item FlakeID from a previous response's itemsPagination.cursor. Lists not in the map start at page 1; cursors for lists not in _path are silently ignored. Response Shape (compact) - results (Copilot clients only) is a { url, title } citation list for client rendering — read list data from lists, not here. - Browse entries emit { id, path, name, created, updated, columns } — no items, no itemsPagination. - Details entries additionally emit { items, itemsPagination }. Keys are shortened: id=itemId, path=full _path, created=createdAt, updated=updatedAt. - columns is always present (empty array when the list has no columns). - columns is declared once per list as [{ id, name, model }] where id is the lp_ FlakeID (use it for columnFilters[].columnId) and model is one of: text-simple, number-simple, date-simple, date-expiry, attachment-simple. Use model to interpret each column's values. - items is an array of { id, value, properties }. properties is a positional array — properties[i] corresponds t…
dashpivot_get_templates
ChatGPTRetrieves app (template) definitions from Dashpivot with field-level metadata. Purpose Gateway to form data. Discover apps, review field definitions, select field IDs before calling dashpivot_get_forms. Prerequisites - For browse queries: call dashpivot_get_workspace_structure first to discover the hierarchy, then pass _path values. - For direct lookup: use appIds with any app identifier (FlakeID, ObjectId, or unique app ID). No _path needed — the server resolves it automatically. - If the user provides a Dashpivot URL, extract the ID from the URL path and pass it to appIds. Scoping Rules - Preferred: Use a project/team _path (e.g., "/ws_xxx/p_xxx") for targeted browse results. - Broader: Using a workspace _path ("/ws_xxx") may return many apps — only use for workspace-level apps or when a narrower _path is unavailable. - Combine _path with appName or templateTags to narrow results further. Parameters - appIds: Look up apps by any identifier — FlakeID (app_xxx), MongoDB ObjectId (24 hex chars), or unique app ID (e.g. TDW-C-JK6AQ). No _path needed. - _path: Required for browse queries, optional when appIds is provided. Use the narrowest paths available (e.g., ["/ws_xxx/p_xxx"]). - appName / templateTags: Filter apps - pageSize (default 25, max 25), pageCursor for pagination Key Behaviour - List/browse queries return app metadata with fieldCount only — look up specific apps by appIds to get full field definitions - Each app includes a _path field — use directly as _path in dashpivot_get_forms (e.g., ["/ws_xxx/p_xxx/app_xxx"]) - For workspace-wide queries, use _path: ["/" + workspaceId] (e.g., ["/ws_xxx"]) - Action templates are listed with kind: 'action'. For open, overdue or assigned actions, call dashpivot_get_actions instead of reading the action template's forms. - A /ws_xxx/app_xxx path returns both workspace-level apps and their team-level deployed copies together, only team-deployed copies have forms. To dashpivot_get_forms, pass in a team-level path /ws_xxx/p_xxx/p_xxx/app_xxx as _path. Field Selection for dashpivot_get_forms When calling dashpivot_get_forms, pass specific field IDs via the optional fieldIds parameter to control which fields are returned. Omitting fieldIds returns ALL fields including media (photo, signature, sketch) which contain large binary data. Select fields based on the task: - For text analysis: use singleLineInput, multiLineInput fields - For date filtering: use date fields - For status checks: use category, yesNoCheckbox fields - Avoid media fields (photo, signature, sketch, attachment) unless specifically needed — they contain large binary data Examples - Browse all apps in a project: { _path: ["/ws_xxx/p_xxx"] } - Find safety templates: { _path: ["/ws_xxx/p_xxx"], templateTags: ["safety"] } - Get field definitions for a specific app: { appIds: ["app_xxx"] } <!-- mcp-router:region-aware-pagination --> Pagination across regions: The response includes pageDetails.regions keyed by region (e.g. au1, uk1). To get the next page, pass pageCursor as a JSON object (not a string) with an entry for each region where isLastPage: false. Example: pageCursor: {"au1": "ws_abc", "uk1": "ws_xyz"}. Omit pageCursor entirely for the first page. pageSize applies per-region — the response may include up to pageSize × N items where N is the number of regions with data.
dashpivot_get_users
ChatGPTRetrieves user information within a workspace's folder hierarchy. Modes - users-in-folder: List the users in a specific folder. - folders-for-user: Given a person's name or email, list which folders they can access within the queried workspace(s). PII Protection Every user in the response has lastName reduced to its initial (e.g. "S") and email masked (e.g. "j*@example.com"). `firstName`, `sitemateUserId`, and `_id` are unmasked. Do not reconstruct or guess full names/emails from the masked values — ask the human if you need the original. When to Use - "Who has access to this project?" → mode "users-in-folder" - "Which folders can <person> access?" / "What is <person>'s access in this workspace?" → mode "folders-for-user" Required Parameters - _path: Array of 1-100 FlakeID paths from dashpivot_get_workspace_structure. Each must be workspace-rooted (e.g. "/ws_xxx" or "/ws_xxx/p_xxx"). Paths may span multiple workspaces. - mode: "users-in-folder" or "folders-for-user" Mode-Specific Parameters - users-in-folder: pageSize, pageCursor. Pass multiple paths to union users across folders — a user who appears in any queried folder is returned once. Lists users granted on the queried folder OR a sub-folder beneath it; access inherited from a PARENT is not reflected (query the parent folder to see its controllers). - folders-for-user: provide `name` or `email` (exact match, takes precedence over name). `name` uses case-insensitive exact equality, not substring/partial — "John" matches users whose firstName OR lastName is exactly "John"; "John Smith" matches firstName "John" AND lastName "Smith". Returns one of: a single user-match with their accessible folders (inheritance-aware — a workspace controller is listed for a queried child folder); a disambiguation signal carrying NO user data when multiple users share the name (ask the human for the exact email, then re-call with `email`); or no-match**. Notes - users-in-folder membership is a superset of folders-for-user reachability. users-in-folder lists a user straight from the permission service regardless of whether the granting folder is still active, so it can include grants on archived/deleted sub-folders that folders-for-user (which resolves to active folders only) will not return. Examples - Users in a project: { _path: ["/ws_xxx/p_xxx"], mode: "users-in-folder" } - Users across multiple projects: { _path: ["/ws_xxx/p_a", "/ws_xxx/p_b"], mode: "users-in-folder" } - Users across workspaces: { _path: ["/ws_A", "/ws_B"], mode: "users-in-folder" } - Folders a user can access: { _path: ["/ws_xxx"], mode: "folders-for-user", name: "John Smith" } - Disambiguate by exact email: { _path: ["/ws_xxx"], mode: "folders-for-user", email: "john.smith@example.com" }
dashpivot_get_workspace_structure
ChatGPTBrowse the Sitemate workspace hierarchy by drilling from workspaces → projects → teams. Returns a level-discriminated page — one of workspaces[], projects[], or teams[] per call, never the full tree. Use _path values from one response as input to the next. When to Call First tool in any workflow. Walk the 3-call pattern below to resolve a workspace name to a project or team _path, then pass that _path to tools like dashpivot_get_templates. Parameters - _path (string[]): omit to list workspaces; ["/ws_xxx"] to list projects in a workspace; ["/ws_xxx/p_yyy"] to list teams in a project. - nameFilter (string): case-insensitive partial match on the entity name at the current _path level. Use short, distinctive substrings ("Acme", not "Acme Construction Pty. Ltd."). - state: "active" (default), "archived", or "deleted". Workspaces don't support "deleted". - pageSize: default 50, max 50. - pageCursor: pass pageDetails.cursor from the previous response. Response Always carries level + instructions[]. Switch on level before accessing arrays: - level: "workspace" → workspaces[] (itemId, _path, name, projectCount, totalTeamCount) - level: "project" → projects[] (itemId, _path, name, teamCount) - level: "team" → teams[] (itemId, _path, name) Empty pages omit the array entirely; check pageDetails.isLastPage before paginating. Worked example (browse → drill → drill) 1. dashpivot_get_workspace_structure({}) → level: "workspace", e.g. _path: "/ws_acme" 2. dashpivot_get_workspace_structure({ _path: ["/ws_acme"] }) → level: "project", e.g. _path: "/ws_acme/p_highway" 3. dashpivot_get_workspace_structure({ _path: ["/ws_acme/p_highway"] }) → level: "team", e.g. _path: "/ws_acme/p_highway/p_safety" Pass the final _path to dashpivot_get_templates to fetch apps at that scope. Cursor-error recovery Cursors are scope-bound to the level that issued them. Reusing a cursor across scopes returns a BadRequestError with a cursorValidationFailureMode discriminator (workspace-cursor-on-drill-down, drill-down-cursor-on-workspace, or unrecognised-prefix). Recovery: drop the cursor and retry without it. Don't try to translate cursors across scopes. <!-- mcp-router:region-aware-pagination --> Pagination across regions: The response includes pageDetails.regions keyed by region (e.g. au1, uk1). To get the next page, pass pageCursor as a JSON object (not a string) with an entry for each region where isLastPage: false. Example: pageCursor: {"au1": "ws_abc", "uk1": "ws_xyz"}. Omit pageCursor entirely for the first page. pageSize applies per-region — the response may include up to pageSize × N items where N is the number of regions with data.
gearbelt_get_asset_context
ChatGPTAssemble the full picture for one asset in a single call: the asset, its open issues, recent work orders, recent inspections, and its schedule-check compliance. When to use - Answer "give me everything on asset X" / "what's the state of E-204?" — returns everything related to one asset (work orders, issues/faults, schedule checks, inspections) in a single call, the way the Assets tab does. - Prefer this over calling gearbelt_get_issues / gearbelt_get_work_orders / gearbelt_get_inspections / gearbelt_get_schedule_checks separately for one asset. - The nested issues / work orders / inspections carry who raised or submitted them (createdBy / submittedBy + ids), so you can answer "who's been working on this asset". Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - assetId (required) — the asset's UUID. Find it with gearbelt_get_assets (its search matches asset code, make, model, registration, or serial), then pass the returned id. - intent / conversationId (optional) — always include for call tracing. Response format Returns an object: - url — absolute web link to this asset's page (the citation source for the record). - asset — id, internalId, manufacturer, model, class, type, registration, state, category, location. - openIssues — up to 20 open issues (each: id, num, title, sev, wo, repair, …). - workOrders — up to 20 recent work orders (each carries its status). - recentInspections — up to 5 most-recent inspections. - compliance — { total, ok, due, overdue, complianceRate, checks[] } over open schedule checks (dueStatus derived overdue/due/ok). - instructions — short guidance strings; read them. Example { "_path": "/ws_4oxc6SXZdYm", "assetId": "<asset id from gearbelt_get_assets>" }
gearbelt_get_assets
ChatGPTList assets (plant, vehicles, tools & equipment) in a Gearbelt workspace. When to use - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - Fetch one page at a time; only request the next page when the user asks for more. - This is a list/search tool. For everything about one asset — its open issues, work orders, recent inspections, and compliance ("full picture", "current state", "everything on E-204") — use this only to resolve the asset code to its id, then call gearbelt_get_asset_context; don't rebuild that picture from separate list calls. - Each row carries the operator (operatedBy name + operatedById), when set. Count operatedById for "who operates the most assets". Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across asset code, make, model, registration, serial. - state (optional) — filter by record state; defaults to active (pass archived/deleted to include those). - types (optional) — restrict to asset type(s). - orderBy / orderDir (optional) — sort field and direction. - intent / conversationId (optional) — always include for call tracing. Prefer search/state/types over paging through everything — filtering server-side is cheaper and more accurate. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. instructions is a short list of guidance strings (result count, pagination, next steps) — read them. Fields returned - id (id) — string — Gearbelt asset UUID - iid (internalId) — string|null — user-facing asset code - mfr (manufacturer) — string|null - mdl (model) — string|null - cls (class) — string|null — free-text class / sub-type - reg (registration) — string|null - sn (serialNumber) — string|null - type (type) — enum — "Assets" | "Tools and Equipment" - state (state) — enum — "active" | "archived" | "deleted" - cat (category) — string|null — category name - loc (location) — string|null — location name - operator (operatedBy) — string|null — name of the user this asset is operated by - operatorId (operatedById) — string|null — stable id of the operator (count/group by this for per-user totals) - created (createdAt) — string — ISO 8601 date-time Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor to fetch the next page. Example { "_path": "/ws_4oxc6SXZdYm" }
gearbelt_get_inspections
ChatGPTList inspections in a Gearbelt workspace, each with its readings and units (e.g. 150 hrs). When to use - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - Fetch one page at a time; only request the next page when the user asks for more. - Each row carries the submitter (submittedBy name + submittedById). Count submittedById for "who submitted the most inspections"; for "who hasn't submitted", diff the submitters against the roster from gearbelt_get_users. Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across inspection number and form name. - formName (optional) — filter to inspections captured with this form/template name. - assetIds (optional) — restrict to inspections on these asset(s), by asset UUID from gearbelt_get_assets (its search finds an asset by code, make, model, registration, or serial). - orderBy / orderDir (optional) — sort field and direction. - intent / conversationId (optional) — always include for call tracing. Prefer filters over paging through everything — filtering server-side is cheaper and more accurate. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. instructions is a short list of guidance strings (result count, pagination, next steps) — read them. Fields returned - id (id) — string — inspection id - num (number) — integer — sequential inspection number - date (inspectionDate) — string — ISO 8601 date-time - readings (readings) — array of { value: number, unit: string, unitName: string } — readings - issues (issueCount) — integer — issues raised on this inspection - asset (asset) — string|null — linked asset internalId - loc (location) — string|null — location name - by (submittedBy) — string|null — name of the user who submitted the inspection - byId (submittedById) — string|null — stable id of that user (count/group by this for per-user totals) - created (createdAt) — string — ISO 8601 date-time Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor to fetch the next page. Example { "_path": "/ws_4oxc6SXZdYm" }
gearbelt_get_issues
ChatGPTList issues (defects/faults raised on assets) in a Gearbelt workspace. When to use - Customers and mechanics call these "faults" or "defects" — a question about faults/defects on an asset maps to this tool. - The first hop of the defect-to-fix loop: an inspection raises an issue (a fault), which becomes a work order, which is resolved by a repair. - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - To find the work order or repair for an issue, read the row's wo (work-order number) and repair (repair id) columns. - An issue whose wo is empty has no work order raised yet — answer "open issues with no work order raised" from this tool alone (filter statuses: ["open"], then keep rows whose wo is null); no gearbelt_get_work_orders call is needed for that. - Each row carries the raiser (createdBy name + createdById). For "who raised the most issues" count createdById over the rows (add createdAt for "this week"). Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across title, description, number, asset, linked work-order/repair numbers. - state (optional) — record state; defaults to active. - severities (optional) — restrict to severity level(s). - statuses (optional) — restrict to issue status(es) (open, closed). - assetIds (optional) — restrict to issues on these asset(s), by asset UUID from gearbelt_get_assets (its search finds an asset by code, make, model, registration, or serial). - createdDate (optional) — ISO 8601 [from, to] range on issue creation. - orderBy / orderDir (optional) — sort field and direction. - intent / conversationId (optional) — always include for call tracing. Prefer filters over paging through everything — filtering server-side is cheaper and more accurate. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. instructions is a short list of guidance strings — read them. Fields returned - id (id) — string — issue id - num (number) — integer — sequential issue number - title (title) — string|null - status (status) — enum|null — "open" | "closed" - sev (severity) — enum|null — "critical" | "high" | "medium" | "low" - source (source) — string|null — inspection, service, manual - asset (asset) — string|null — linked asset internalId - loc (location) — string|null — location name - days (daysOpen) — integer — days open (frozen at close when closed) - wo (workOrder) — integer|null — linked work-order number - repair (repairId) — string|null — linked repair id - closed (closedAt) — string|null — ISO 8601 date-time - by (createdBy) — string|null — name of the user who raised the issue - byId (createdById) — string|null — stable id of that user (count/group by this for "who raised the most") - created (createdAt) — string — ISO 8601 date-time - state (state) — enum — "active" | "archived" | "deleted" Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor. Example { "_path": "/ws_4oxc6SXZdYm", "statuses": ["open"], "severities": ["critical"] }
gearbelt_get_repairs
ChatGPTList repairs (work done to resolve issues) in a Gearbelt workspace. When to use - The final hop of the defect-to-fix loop: a repair records the work that closed one or more issues. This is the maintenance-completion record — distinct from gearbelt_get_work_orders, which is the job/request record. - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - To find which issue a repair closed, call gearbelt_get_issues and filter by the repair — issues carry the repair id. - Aggregate questions over repair activity (repairs per asset, throughput, repair counts) are answerable from this tool alone — repair rows carry the asset internalId, technician, and repair date, so you don't need gearbelt_get_work_orders to compute them. Break these down by asset category via a gearbelt_get_assets join (internalId → category); repair rows carry no category. Mean-time-to-repair is a fault-to-fix duration, so it needs the issue's raised date from gearbelt_get_issues (or read that tool's daysOpen column directly), not just the repair date here. - Each row carries the technician (repairedBy name + repairedById). For "most productive mechanic / who logged the most repairs" count repairedById over the rows. Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across repair number, asset, technician, form name, and form answers. - assetIds (optional) — restrict to repairs on these asset(s), by asset UUID from gearbelt_get_assets (its search finds an asset by code, make, model, registration, or serial). - formName (optional) — filter to repairs captured with this form/template name. - repairDate (optional) — ISO 8601 [from, to] range on the repair date. - orderBy / orderDir (optional) — sort field and direction. - intent / conversationId (optional) — always include for call tracing. Only active repairs are returned. Prefer filters over paging through everything. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. Fields returned - id (id) — string — repair id - num (number) — integer — sequential repair number - date (repairDate) — string — ISO 8601 date-time repair carried out - asset (asset) — string|null — linked asset internalId - form (form) — string|null — repair form/template name - by (repairedBy) — string|null — name of the user who logged the repair - byId (repairedById) — string|null — stable id of that user (count/group by this for per-user totals) - created (createdAt) — string — ISO 8601 date-time Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor. Example { "_path": "/ws_4oxc6SXZdYm" }
gearbelt_get_schedule_checks
ChatGPTList schedule checks (recurring maintenance/compliance obligations per asset) in a Gearbelt workspace. When to use - The servicing / compliance loop: a schedule produces a check per asset (a "service due" obligation, e.g. a 500-hour service), whose derived status is overdue / due / ok. - Answer "what's due or overdue?" / "what servicing is coming up?" / "which assets are due (or overdue) for service?" / "when is the next service?" — read the dueStatus column (overdue/due/ok; ok = "on track" in the product's green/red wording) and sort by dueProgress desc to surface the most overdue first. - "Due for service" / "overdue for service" / "next service due" all map to this tool. Assets themselves carry no service-due date field, so don't look for one on gearbelt_get_assets — the dueStatus / dueDate on a schedule check is the source of truth for servicing. - For a workspace/grouped rollup (PM compliance rate, audit view), use gearbelt_get_schedule_compliance instead. - Each row carries the completer (completedBy/completedById) when the check is done. Count completedById for "who completed the most checks". Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across check number, asset, and schedule name. - assetIds (optional) — restrict to checks on these asset(s), by asset UUID from gearbelt_get_assets (its search finds an asset by code, make, model, registration, or serial). - checkStatus (optional) — lifecycle status (open, closed). NOTE: this is NOT the derived overdue/due/ok status — that is the output-only dueStatus column. - dueDate (optional) — ISO 8601 [from, to] range on the due date. - orderBy / orderDir (optional) — sort field and direction (default dueProgress desc). - intent / conversationId (optional) — always include for call tracing. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. The dueStatus column is derived server-side (overdue/due/ok). Fields returned - id (id) — string — schedule check id - num (number) — integer|null — sequential check number - status (status) — enum — "open" | "closed" | "void" - dueStatus (dueStatus) — enum — "overdue" | "due" | "ok" (derived; ok = "on track") - progress (dueProgress) — number|null — percent toward due (>100 = overdue) - due (dueDate) — string|null — ISO 8601 date-time next due - daysLeft (daysRemaining) — integer|null — days until due (negative = overdue) - asset (asset) — string|null — linked asset internalId - schedule (schedule) — string|null — schedule name - completed (completedAt) — string|null — ISO 8601 date-time completed - by (completedBy) — string|null — name of the user who completed the check - byId (completedById) — string|null — stable id of that user (count/group by this for per-user totals) - wo (workOrder) — integer|null — linked work-order number Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor. Example { "_path": "/ws_4oxc6SXZdYm", "checkStatus": ["open"], "orderBy": "dueProgress", "orderDir": "desc" }
gearbelt_get_schedule_compliance
ChatGPTSummarise schedule-check compliance across a Gearbelt workspace — counts by status and a compliance rate. When to use - Answer "how compliant are we?" / "what's our PM compliance?" / "what's our compliance rate?" / "how much servicing is overdue?" without paging through individual checks. - Backs the audit / reporting view of servicing compliance (service-due vs overdue across the fleet). - For the individual checks behind the numbers, use gearbelt_get_schedule_checks. Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - assetIds (optional) — scope the rollup to specific asset(s), by asset UUID from gearbelt_get_assets (use its search to find an asset by code, make, model, registration, or serial). - dueDate (optional) — ISO 8601 [from, to] range on the due date. - groupBy (optional) — none (default, workspace total), asset, schedule, or location. - intent / conversationId (optional) — always include for call tracing. Response format Returns an object: { url, title, subtitle, total, ok, due, overdue, complianceRate, groupBy, groups, instructions }. - url / title / subtitle — a citation for this rollup, linking to the workspace's schedule checks; used only for client citation rendering. - total — open checks in scope. ok / due / overdue — counts by derived status. - complianceRate — ok / total × 100 (one decimal); 0 when there are no open checks. - groups — per-groupBy breakdown (empty when groupBy is none); each has groupKey, groupLabel, and the same counts. - instructions — short guidance strings; read them. Example { "_path": "/ws_4oxc6SXZdYm", "groupBy": "location" }
gearbelt_get_users
ChatGPTList the members (users) of a Gearbelt workspace — the workspace roster. When to use - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - Resolve a person id to a name: a row's id matches the ...ById columns on records (createdById, submittedById, repairedById, completedById). - For "who hasn't submitted / done X", get this roster and diff it against the users who did — e.g. the submittedById values from gearbelt_get_inspections. Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - search (optional) — free-text across name, email, and username. - userType (optional) — "contributors" (default) | "sitemate-users" | "all". - limit (optional) — max rows this page (default 30, max 100). - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - intent / conversationId (optional) — always include for call tracing. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. Fields returned - id (id) — string — user id (matches the ...ById columns on records) - name (name) — string|null — full name - roles (roles) — array of string — the user's workspace role(s) - status (status) — string — active | pending Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor. Example { "_path": "/ws_4oxc6SXZdYm" }
gearbelt_get_work_orders
ChatGPTList work orders (maintenance and repair jobs) in a Gearbelt workspace. When to use - Call gearbelt_get_workspaces first to get a workspace _path, then call this tool with it. - Fetch one page at a time; only request the next page when the user asks for more. - The authoritative source for work-order detail on an issue: read an issue's wo column (via gearbelt_get_issues), then use this tool for the full work order. - Work-order status is an output column, not a server-side filter — there is no status param; fetch and read/group open vs closed on the returned rows. The available server-side filters are priorities, assignedToCurrentUser, and assetIds. - To scope to one asset, resolve its human code (e.g. E-204) to a UUID with gearbelt_get_assets search, then pass it as assetIds — there is no lookup by human-readable asset code. - Each row carries the raiser (createdBy/createdById) and its assignees (assignees names + assigneeIds stable ids, aligned). Count createdById or assigneeIds for "who raised / is assigned the most work orders". Parameters - _path (required) — workspace path, e.g. "/ws_4oxc6SXZdYm". - pageCursor (optional) — opaque cursor from a previous response's nextPageCursor. - limit (optional) — max rows this page (default 30, max 100). - search (optional) — free-text across title, number, PO. - state (optional) — filter by record state; defaults to active (pass archived/deleted to include those). - priorities (optional) — restrict to priority level(s). - assignedToCurrentUser (optional) — only work orders assigned to the caller. - assetIds (optional) — restrict to work orders on these asset(s), by asset UUID from gearbelt_get_assets (its search finds an asset by code, make, model, registration, or serial). - orderBy / orderDir (optional) — sort field and direction. - intent / conversationId (optional) — always include for call tracing. Prefer filters over paging through everything — filtering server-side is cheaper and more accurate. Response format (columnar, compact) Returns { fields, rows, nextPageCursor, instructions, results }. results is a parallel array (one { url, title, subtitle } per row) used only for client citation rendering — ignore it for data and read rows. fields lists the column short-names once; each entry in rows is a positional array aligned to fields — read rows[i][k] against fields[k]. Absent values are null. instructions is a short list of guidance strings (result count, pagination, next steps) — read them. Fields returned - id (id) — string — work order UUID - num (number) — integer — sequential work-order number - title (title) — string|null - status (status) — enum — "Open" | "Closed" - prio (priority) — enum|null — "critical" | "high" | "medium" | "low" - due (dueDate) — string|null — ISO 8601 date-time - closed (closedAt) — string|null — ISO 8601 date-time - state (state) — enum — "active" | "archived" | "deleted" - asset (asset) — string|null — linked asset internalId - loc (location) — string|null — location name - by (createdBy) — string|null — name of the user who raised the work order - byId (createdById) — string|null — stable id of that user (count/group by this for per-user totals) - assignees (assignees) — array of string — names of the users this work order is assigned to - assigneeIds (assigneeIds) — array of string — stable ids of the assignees, aligned to assignees - created (createdAt) — string — ISO 8601 date-time Pagination nextPageCursor is null on the last page; otherwise pass it back as pageCursor to fetch the next page. Example { "_path": "/ws_4oxc6SXZdYm" }
gearbelt_get_workspaces
ChatGPTList the Gearbelt workspaces the caller can access. This is the entry point — call it first to obtain a workspace _path for the other Gearbelt tools. When to use - Call this before gearbelt_get_assets / gearbelt_get_work_orders / gearbelt_get_inspections, which all require a _path. - An empty result means the caller has no Gearbelt workspace access. Parameters - intent / conversationId (optional) — always include for call tracing; see the parameter hints. Fields returned Returns { workspaces, results, instructions }. results is a parallel array (one { url, title, subtitle } per workspace) used only for client citation rendering — ignore it for data and read workspaces. Each workspaces entry: - _path — string, pass verbatim as _path to the other Gearbelt tools. - name — string, workspace display name. - workspaceId — string, workspace flake id (ws_…). - role — the caller's role on this workspace.
get-apps
ChatGPTRetrieves app (template) definitions from Dashpivot with field-level metadata. Purpose Gateway to form data. Discover apps, review field definitions, select field IDs before calling get-forms. Prerequisites - For browse queries: call get-workspace-structure first to discover the hierarchy, then pass _path values. - For direct lookup: use appIds with any app identifier (FlakeID, ObjectId, or unique app ID). No _path needed — the server resolves it automatically. - If the user provides a Dashpivot URL, extract the ID from the URL path and pass it to appIds. Scoping Rules - Preferred: Use a project/team _path (e.g., "/ws_xxx/p_xxx") for targeted browse results. - Broader: Using a workspace _path ("/ws_xxx") may return many apps — only use for workspace-level apps or when a narrower _path is unavailable. - Combine _path with appName or templateTags to narrow results further. Parameters - appIds: Look up apps by any identifier — FlakeID (app_xxx), MongoDB ObjectId (24 hex chars), or unique app ID (e.g. TDW-C-JK6AQ). No _path needed. - _path: Required for browse queries, optional when appIds is provided. Use the narrowest paths available (e.g., ["/ws_xxx/p_xxx"]). - appName / templateTags: Filter apps - pageSize (default 25, max 25), pageCursor for pagination Key Behaviour - List/browse queries return app metadata with fieldCount only — look up specific apps by appIds to get full field definitions - Each app includes a _path field — use directly as _path in get-forms (e.g., ["/ws_xxx/p_xxx/app_xxx"]) - For workspace-wide queries, use _path: ["/" + workspaceId] (e.g., ["/ws_xxx"]) Field Selection for get-forms When calling get-forms, pass specific field IDs via the optional fieldIds parameter to control which fields are returned. Omitting fieldIds returns ALL fields including media (photo, signature, sketch) which contain large binary data. Select fields based on the task: - For text analysis: use singleLineInput, multiLineInput fields - For date filtering: use date fields - For status checks: use category, yesNoCheckbox fields - Avoid media fields (photo, signature, sketch, attachment) unless specifically needed — they contain large binary data Examples - Browse all apps in a project: { _path: ["/ws_xxx/p_xxx"] } - Find safety templates: { _path: ["/ws_xxx/p_xxx"], templateTags: ["safety"] } - Get field definitions for a specific app: { appIds: ["app_xxx"] } <!-- mcp-router:region-aware-pagination --> Pagination across regions: The response includes pageDetails.regions keyed by region (e.g. au1, uk1). To get the next page, pass pageCursor as a JSON object (not a string) with an entry for each region where isLastPage: false. Example: pageCursor: {"au1": "ws_abc", "uk1": "ws_xyz"}. Omit pageCursor entirely for the first page. pageSize applies per-region — the response may include up to pageSize × N items where N is the number of regions with data.
get-forms
ChatGPTRetrieves form data (filled-in records) for summarization, analysis, and reporting. When to Use - If the user provides a specific _path, call get-forms directly — do NOT call get-workspace-structure or get-apps first. - If the user asks about forms without a path, follow the standard discovery workflow. - If get-forms returns 0 results, check the instructions field for diagnostic guidance before making follow-up calls. Required Parameter - _path: Array of FlakeID paths (max 100). Use _path values from get-apps or get-workspace-structure (e.g., ["/ws_xxx/p_xxx/app_xxx"] or ["/ws_xxx"]). Key Parameters - formName / fieldFilters: Filter forms - workflowStep: Filter by workflow column — accepts position numbers (1, 2) and/or column name strings ("Supervisor Approval"). Case-insensitive. - createdDate: Filter by creation date range ({ after?, before? } — ISO 8601 strings) - fieldIds: Return only specific fields (use IDs from get-apps) - pageSize (default 10, max 10), pageCursor for pagination Response Format (compact) Compressed JSON with ~63% fewer tokens. Field values are lossless. Forms are grouped by app. Structure: - apps: array of app groups, each containing: - appPath: shared app path for this group - fields: array of { name, kind } — field definitions declared once per app - forms: array of { id, name, num, workflowCol, created, by, values } — each form's values array is positionally mapped to fields - Shortened keys: id=itemId, num=automatedFormNumber, workflowCol.pos=workflowColumn.position, workflowCol.name=workflowColumn.name, created=createdAt, by=createdBy.name - Pagination: pass pageDetails.cursor back as pageCursor to fetch the next page. pageDetails.pageNumber is informational only. Example response: `` {"apps":[{"appPath":"/ws_xxx/p_xxx/app_xxx","fields":[{"name":"Inspector","kind":"singleLineInput"},{"name":"Status","kind":"category"}],"forms":[{"id":"form_xxx","name":"Inspection #1","num":"SI-001","workflowCol":{"pos":2,"name":"Supervisor Approval"},"created":"2026-03-20T10:00:00Z","by":"John","values":["Michael",[{"name":"Pass","value":"pass"}]]}]}],"totalFormCount":42,"instructions":["Sending form 1 of 42.","More results available. Pass the cursor value as pageCursor to fetch the next page."],"pageDetails":{"cursor":"form_xxx","size":10,"isLastPage":false,"pageNumber":1}} ` To read a value: apps[i].forms[j].values[k] corresponds to apps[i].fields[k]. Field IDs for fieldFilters/fieldIds are available from get-apps. Key Behaviour - Results are sorted newest first (most recent form at index 0) - Each field has { _id, name, kind, value } — value contains the extracted data - Returns up to 10 forms per response — use pageDetails.cursor for pagination when more results exist - More specific _path values return faster results - Field value structures vary by kind — see get-apps field definitions for type metadata Examples - Get all forms for an app: { _path: ["/ws_xxx/p_xxx/app_xxx"] } - Forms from Q1 2026: { _path: ["/ws_xxx/p_xxx/app_xxx"], createdDate: { after: "2026-01-01T00:00:00Z", before: "2026-04-01T00:00:00Z" } } - Return only text fields: { _path: ["/ws_xxx/p_xxx/app_xxx"], fieldIds: ["fi_xxx", "fi_yyy"] } - Forms in approval step: { _path: ["/ws_xxx/p_xxx/app_xxx"], workflowStep: ["Supervisor Approval"] } - Forms in columns 1 or 2: { _path: ["/ws_xxx/p_xxx/app_xxx"], workflowStep: [1, 2] }`
get-lists
ChatGPTDeprecated This tool still works and is fully supported. It has been renamed to dashpivot_get_lists. Prefer dashpivot_get_lists when it is available to you. Behaviour, parameters and responses are identical, so calls made here still return the same results. Retrieves Dashpivot lists (spreadsheet-like data containers): columns, items, and property values. Lists power list fields and list property columns in forms — use this to understand what data populates form dropdowns and lookup fields. Modes (dispatched by leaf prefix of each _path) - Browse (leaf is ws_ or p_): returns list metadata plus columns (so the LLM can see what each list is shaped like and read columns[].id for follow-up columnFilters). items and itemsPagination are omitted. Use when discovering which lists exist under a workspace/project. - Details (leaf is li_): returns full data for the named list — columns, items, and property values. Use when a specific list has been identified to inspect. columns is always present on every list entry (empty array when the list has no columns). Browse and details paths can be mixed in one call — each entry resolves on its own leaf prefix. When to Use - If the user provides a specific _path, call dashpivot_get_lists directly — do NOT call dashpivot_get_workspace_structure first. - If the user asks about lists without a path, follow the standard discovery workflow: browse first, then narrow to a li_ path for details. - If dashpivot_get_lists returns 0 results, check the instructions field for diagnostic guidance. Required Parameter - _path: Array of FlakeID paths (max 100). Workspace/project paths (e.g., ["/ws_xxx"], ["/ws_xxx/p_xxx"]) trigger browse mode; list paths (e.g., ["/ws_xxx/li_xxx"]) trigger details mode. Key Parameters - listName: Filter by list name (case-insensitive partial match) — narrows which lists are returned in browse mode. - itemValue: Filter items by display value — the Item column shown in the list library (case-insensitive partial match). Only meaningful in details mode. - columnFilters: Filter items by column values. AND across entries, OR within each entry's queries. Each filter has a columnId (lp_ FlakeID — read from columns[].id in a prior details response), queries (array of one or more string/number values for OR matching within the entry), and an optional match mode controlling how each query compares to the cell value: "contains" (default — case-insensitive substring), "exact" (case-insensitive equality — use for IDs, codes, and precise numeric matches: queries: ["1"] with match: "exact" matches "1" only, NOT "10" or "9991"), or "prefix" (case-insensitive starts-with). To find rows where a column is empty / has no value, fetch the list without columnFilters and look for null in each item's positional properties array at the relevant column index. Only items matching ALL filter entries are returned. Only meaningful in details mode. - pageSize (default 25, max 25), pageCursor for list-level pagination. - itemPageSize (default 100, max 1000) — items per details list per page. Silently ignored for browse paths. - itemCursors — per-list item pagination cursors keyed by full list path (e.g. { "/ws_xxx/li_yyy": "lr_..." }). Each value is an item FlakeID from a previous response's itemsPagination.cursor. Lists not in the map start at page 1; cursors for lists not in _path are silently ignored. Response Shape (compact) - results (Copilot clients only) is a { url, title } citation list for client rendering — read list data from lists, not here. - Browse entries emit { id, path, name, created, updated, columns } — no items, no itemsPagination. - Details entries additionally emit { items, itemsPagination }. Keys are shortened: id=itemId, path=full _path, created=createdAt, updated=updatedAt. - columns is always present (empty array when the list has no columns). - columns is declared once per list as [{ id, name, model }] where id is the lp_ FlakeID (use it for columnFilters[].columnId) and `mod…
get-users
ChatGPTDeprecated This tool still works and is fully supported. It has been renamed to dashpivot_get_users. Prefer dashpivot_get_users when it is available to you. Behaviour, parameters and responses are identical, so calls made here still return the same results. Retrieves user information within a workspace's folder hierarchy. Modes - users-in-folder: List the users in a specific folder. - folders-for-user: Given a person's name or email, list which folders they can access within the queried workspace(s). PII Protection Every user in the response has lastName reduced to its initial (e.g. "S") and email masked (e.g. "j*@example.com"). `firstName`, `sitemateUserId`, and `_id` are unmasked. Do not reconstruct or guess full names/emails from the masked values — ask the human if you need the original. When to Use - "Who has access to this project?" → mode "users-in-folder" - "Which folders can <person> access?" / "What is <person>'s access in this workspace?" → mode "folders-for-user" Required Parameters - _path: Array of 1-100 FlakeID paths from dashpivot_get_workspace_structure. Each must be workspace-rooted (e.g. "/ws_xxx" or "/ws_xxx/p_xxx"). Paths may span multiple workspaces. - mode: "users-in-folder" or "folders-for-user" Mode-Specific Parameters - users-in-folder: pageSize, pageCursor. Pass multiple paths to union users across folders — a user who appears in any queried folder is returned once. Lists users granted on the queried folder OR a sub-folder beneath it; access inherited from a PARENT is not reflected (query the parent folder to see its controllers). - folders-for-user: provide `name` or `email` (exact match, takes precedence over name). `name` uses case-insensitive exact equality, not substring/partial — "John" matches users whose firstName OR lastName is exactly "John"; "John Smith" matches firstName "John" AND lastName "Smith". Returns one of: a single user-match with their accessible folders (inheritance-aware — a workspace controller is listed for a queried child folder); a disambiguation signal carrying NO user data when multiple users share the name (ask the human for the exact email, then re-call with `email`); or no-match**. Notes - users-in-folder membership is a superset of folders-for-user reachability. users-in-folder lists a user straight from the permission service regardless of whether the granting folder is still active, so it can include grants on archived/deleted sub-folders that folders-for-user (which resolves to active folders only) will not return. Examples - Users in a project: { _path: ["/ws_xxx/p_xxx"], mode: "users-in-folder" } - Users across multiple projects: { _path: ["/ws_xxx/p_a", "/ws_xxx/p_b"], mode: "users-in-folder" } - Users across workspaces: { _path: ["/ws_A", "/ws_B"], mode: "users-in-folder" } - Folders a user can access: { _path: ["/ws_xxx"], mode: "folders-for-user", name: "John Smith" } - Disambiguate by exact email: { _path: ["/ws_xxx"], mode: "folders-for-user", email: "john.smith@example.com" }
get-workspace-structure
ChatGPTRetrieves workspace hierarchy (workspaces > projects > teams) with permission filtering. When to Call This is the FIRST tool to call in any workflow. Use it to discover the workspace structure before querying apps or forms. Present the returned structure to the user and let them choose which project or team to explore. Pass the returned _path values directly as the _path parameter to get-apps. Parameters - _path: Optional path(s) to scope the query (e.g., ["/ws_xxx"]) - workspaceName: Filter workspaces by name - pageSize (default 25, max 25), pageCursor for pagination Key Behaviour - Always returns the full hierarchy: workspaces > projects > teams - The response always includes the parent workspace ID (ws_xxx) for context, even for users who only have project/team-level access. Always prefer passing the project/team IDs (p_xxx) to get-apps, not the workspace ID. Search Tips Use short, distinctive substrings for workspaceName (e.g., "Acme" instead of "Acme Construction Pty. Ltd."). The search normalizes punctuation and whitespace for fuzzy matching. Example {} — discover all workspaces (no parameters needed) { workspaceName: "Acme" } — find a specific workspace by short name <!-- mcp-router:region-aware-pagination --> Pagination across regions: The response includes pageDetails.regions keyed by region (e.g. au1, uk1). To get the next page, pass pageCursor as a JSON object (not a string) with an entry for each region where isLastPage: false. Example: pageCursor: {"au1": "ws_abc", "uk1": "ws_xyz"}. Omit pageCursor entirely for the first page. pageSize applies per-region — the response may include up to pageSize × N items where N is the number of regions with data.
sitemate_suggest
ChatGPTSignals a missing or unclear capability in the Sitemate toolset. Behavior Read-only. This tool creates, updates, and deletes nothing in Sitemate and reads no user data. It returns a fixed acknowledgement, never blocks, and never counts as a failure. When To Call - You cannot answer the user's Sitemate-related requests with the listed tools at all. - You can answer it, but only by chaining multiple Sitemate discovery tools together. That friction is the signal. - The user uses a Sitemate domain noun that isn't a parameter or tool name in the schema (e.g., "incidents", "RFIs", "defects"). - Do NOT call for non-Sitemate requests (web search, weather, Slack messages). How To Call - Call early and often in parallel with your other tool calls. - It is free to call, does not block, and does NOT count as a failure. - Once per stuck moment is enough — don't repeat the same suggestion in a conversation. - Do not treat it as an alternative to answering; it only signals the gap. Parameters - intent (recommended): Plain-language description of what the user actually asked for. Be concrete — "show forms past their due date" beats "find late stuff". - suggestedToolName (required): Your guess at what the tool would be called, in snake_case (e.g. "dashpivot_get_forms"). - attemptedTools (optional): Array of tool names you already tried / used as a workaround (e.g., ["dashpivot_get_workspace_structure", "dashpivot_get_templates", "dashpivot_get_forms"]). Non-empty = friction report; empty = no workaround attempted. - conversationId (recommended): Same UUID across all tool calls answering the user's question, so calls can be correlated. Response Format Returns a fixed acknowledgement — there is no payload to act on: `` { "logged": true, "message": "Feedback logged." } ` The response is informational only; it confirms the signal was received and exposes no Sitemate data. Examples - Domain noun + chained Sitemate discovery: { "intent": "show me the top 10 RFIs across my workspace", "suggestedToolName": "dashpivot_get_rfis", "attemptedTools": ["dashpivot_get_workspace_structure", "dashpivot_get_templates", "dashpivot_get_forms"], "conversationId": "abc-123" } - Sitemate filter not exposed: { "intent": "find all overdue forms in the middle of a safety audit", "suggestedToolName": "dashpivot_get_overdue_forms", "attemptedTools": ["dashpivot_get_forms"], "conversationId": "abc-123" } - True gap in Sitemate toolset: { "intent": "create a new Sitemate template from scratch", "suggestedToolName": "dashpivot_create_template", "conversationId": "abc-123" }`
suggest
ChatGPTDeprecated This tool still works and is fully supported. It has been renamed to sitemate_suggest. Prefer sitemate_suggest when it is available to you. Behaviour, parameters and responses are identical, so calls made here still return the same results. Signals a missing or unclear capability in the Sitemate toolset. Behavior Read-only. This tool creates, updates, and deletes nothing in Sitemate and reads no user data. It returns a fixed acknowledgement, never blocks, and never counts as a failure. When To Call - You cannot answer the user's Sitemate-related requests with the listed tools at all. - You can answer it, but only by chaining multiple Sitemate discovery tools together. That friction is the signal. - The user uses a Sitemate domain noun that isn't a parameter or tool name in the schema (e.g., "incidents", "RFIs", "defects"). - Do NOT call for non-Sitemate requests (web search, weather, Slack messages). How To Call - Call early and often in parallel with your other tool calls. - It is free to call, does not block, and does NOT count as a failure. - Once per stuck moment is enough — don't repeat the same suggestion in a conversation. - Do not treat it as an alternative to answering; it only signals the gap. Parameters - intent (recommended): Plain-language description of what the user actually asked for. Be concrete — "show forms past their due date" beats "find late stuff". - suggestedToolName (required): Your guess at what the tool would be called, in snake_case (e.g. "dashpivot_get_forms"). - attemptedTools (optional): Array of tool names you already tried / used as a workaround (e.g., ["dashpivot_get_workspace_structure", "dashpivot_get_templates", "dashpivot_get_forms"]). Non-empty = friction report; empty = no workaround attempted. - conversationId (recommended): Same UUID across all tool calls answering the user's question, so calls can be correlated. Response Format Returns a fixed acknowledgement — there is no payload to act on: `` { "logged": true, "message": "Feedback logged." } ` The response is informational only; it confirms the signal was received and exposes no Sitemate data. Examples - Domain noun + chained Sitemate discovery: { "intent": "show me the top 10 RFIs across my workspace", "suggestedToolName": "dashpivot_get_rfis", "attemptedTools": ["dashpivot_get_workspace_structure", "dashpivot_get_templates", "dashpivot_get_forms"], "conversationId": "abc-123" } - Sitemate filter not exposed: { "intent": "find all overdue forms in the middle of a safety audit", "suggestedToolName": "dashpivot_get_overdue_forms", "attemptedTools": ["dashpivot_get_forms"], "conversationId": "abc-123" } - True gap in Sitemate toolset: { "intent": "create a new Sitemate template from scratch", "suggestedToolName": "dashpivot_create_template", "conversationId": "abc-123" }`
dashpivot_get_forms
Claudedashpivot_get_lists
Claudedashpivot_get_templates
Claudedashpivot_get_users
Claudedashpivot_get_workspace_structure
Claudegearbelt_get_asset_context
Claudegearbelt_get_assets
Claudegearbelt_get_inspections
Claudegearbelt_get_issues
Claudegearbelt_get_repairs
Claudegearbelt_get_schedule_checks
Claudegearbelt_get_schedule_compliance
Claudegearbelt_get_users
Claudegearbelt_get_work_orders
Claudegearbelt_get_workspaces
Claudeget-apps
Claudeget-forms
Claudeget-lists
Claudeget-users
Claudeget-workspace-structure
Claudesitemate_suggest
Claudesuggest
Claude
