activate_custom_connector_version
ChatGPTMake an existing published version active, including an earlier version for rollback. You must be an editor with edit access to every Data Mart that follows the active version. If you do not have this access, ask a project admin or request edit access. Draft versions cannot be activated. Activation changes future runs of Data Marts that follow the active version. Data Marts pinned to a version keep that version.
add_destination
ChatGPTAdds a report-delivery destination. Behavior depends on destination_type: for google_sheets, returns a link to a simple in-app "Connect Google Sheets" page — the user must be signed in to OWOX (prompted if not) and a member of this project (asked to request access if not); on the page they click to start Google OAuth, and the destination is created automatically as soon as they approve access — no extra save step; the person who completed it can use it in their own reports right away, but it starts unshared for everyone else on the project — another project member cannot use it until a human shares it — this call does NOT return a destination_id, because the destination does not exist yet, and its name is not known in advance either (the user sets it directly in the form, this tool never pre-fills it); after the user confirms they completed it, call list_destinations and filter to google_sheets entries whose connectedGoogleAccount matches who the user expected — never pick by createdAt/recency, another destination may be created concurrently by someone else; if more than one entry still matches, ask the user which one they mean instead of guessing; for email, slack, and teams, creates the destination directly and requires the emails parameter; for google_chat, MCP supports channel-email delivery only and also requires emails — direct webhook delivery is configured in the OWOX UI/API, and its secret URL must not be sent through MCP/chat; no OAuth is involved and destination_id is returned immediately; for looker_studio (pull-based connector), creates the destination directly and returns destination_id immediately — no OAuth, no emails needed; the connector credentials (including the Destination Secret Key/Token) are never sent through MCP/chat — the user must open the destination in the OWOX Data Marts UI to copy them.
add_report
ChatGPTCreate an OWOX report that exports a data mart to an existing destination (create one with add_destination if the project has none — check list_destinations first). Use when the user wants a refreshable export or delivery to Google Sheets, email, Slack, Microsoft Teams, Google Chat, or Looker Studio. Create one report per user request, then change it with update_report when the user asks to add a filter, sort, aggregation, or rename it — do not create another report for the same data: the tool refuses a report whose fields duplicate one you already created on this data mart and destination (error_code similar_report_exists). For push destinations, the new report runs immediately by default: this starts one billed Report Run and delivers data, then initial_run returns the run_id to poll with get_report_run_status. Set run_immediately=false only when the user explicitly wants to create configuration without delivering data, such as before adding a schedule. Every destination type accepts the same optional output controls as query_data_mart — filters, slices, aggregations, date_buckets, sort — applied on each run: when the user asks to export numbers they saw in a query, copy those parameters verbatim from that query so the report matches what they saw. Google Sheets: a new Google Sheet is created automatically (an external Google Drive side effect) with its file and sheet named after name, and linked to the report; pass spreadsheet_id to add the report as a sheet of an existing spreadsheet instead, so several related exports share one document. Looker Studio is pull-based, never runs through this tool, and accepts no name; omit run_immediately or set it false. Email, Slack, Microsoft Teams, Google Chat: requires message; the default initial run sends it to the configured recipients or channels.
create_context
ChatGPTCreate a business Context in the connected OWOX project. Requires a project admin. Provide a name and optionally a description and icon. Omitted or null descriptions are empty; an omitted or null icon uses the default.
create_custom_connector
ChatGPTCreate a custom connector with its first draft in the connected project. You must be an editor. The connector is not runnable until publish_custom_connector publishes a version. Provide a unique, immutable name, a title and the complete manifest. Follow https://docs.owox.com/docs/connectors/manifest-reference.llms.txt for the manifest format. Use parameter references for credentials instead of literal secret values. Give the user the returned Connector Builder url to open the draft in OWOX.
create_report_run_schedule
ChatGPTCreates a new recurring run schedule for a report. Translate the user's natural-language schedule ("every Monday at 9am", "daily at midnight") into a standard 5-field cron expression before calling (e.g. "0 9 1"). This creates an additional schedule and does not replace, delete, or update existing schedules for the same report. To change an existing schedule, first call list_report_run_schedules and then call update_report_run_schedule with the specific trigger_id. time_zone must be a valid IANA timezone (e.g. "Europe/Kyiv"); if the user does not specify one, default to UTC and confirm with them. is_active defaults to true.
delete_context
ChatGPTDelete a Context in the connected OWOX project. Requires a project admin. Use get_context_impact first; deletion fails while any attachment remains. With user approval, remove member assignments using set_context_members with assigned_user_ids: []. Ask the user to detach Data Marts, Storages, Destinations and user provisioning defaults in the OWOX web app; these detach operations are not available through MCP.
delete_custom_connector
ChatGPTSoft-delete a custom connector and make its name available for reuse. You must be an editor. Deletion fails if any Data Mart references the connector, including a pinned version. Before retrying, reconfigure or remove those references in the OWOX web app. Do not delete Data Marts to bypass this restriction.
delete_report
ChatGPTDelete a report by id. The report stops running and disappears from the project; the underlying data mart, destination, and any already-exported documents are not affected. This cannot be undone.
delete_report_run_schedule
ChatGPTRemoves the single report run schedule identified by trigger_id (get it from list_report_run_schedules). Only that schedule is removed — the Report and any other schedules it may have are left intact. The response echoes the removed trigger_id and report_id with schedule: null to confirm that specific schedule is gone; check list_report_run_schedules if you need to know whether other schedules remain.
get_context_impact
ChatGPTInspect a Context before deleting it: return counts of attached Data Marts, Storages, Destinations, members and user provisioning defaults, plus affected member IDs. Requires a project admin.
get_custom_connector
ChatGPTRead custom connector metadata and all version summaries, with the oldest version first. The result includes a Connector Builder url to open the connector in OWOX. The result does not include manifests. Use list_custom_connectors to find connector_id. As an editor, use get_custom_connector_version to read a draft or published manifest.
get_custom_connector_fields
ChatGPTRead node and field schemas from a published custom connector version. Omit version to use the active version. Draft versions are not available through this tool. The result includes primary keys and default fields where defined. Nested schema keys use the same camelCase format as the connector HTTP API.
get_custom_connector_specification
ChatGPTRead parameter schemas from a published custom connector version. Omit version to use the active version. Draft versions are not available through this tool. The result excludes secret parameter values and OAuth internals. Nested schema keys use the same camelCase format as the connector HTTP API.
get_custom_connector_version
ChatGPTRead the complete stored manifest of a draft or published version. Get the version number from get_custom_connector. You must be an editor because a manifest can contain literal credentials. Treat returned manifests as sensitive data. Do not repeat credential values in conversation.
get_data_mart_details_by_id
ChatGPTGet available details for a specific published OWOX Data Mart by data_mart_id, including its URL, attached context IDs and names, native output fields, and (only on explicit request) joined_fields contributed by blended/joined data marts. Use detail_level=native by default: it avoids exposing irrelevant joined fields and keeps the response fast. Request detail_level=with_joined_fields only when the question truly needs a joined Data Mart. Use displayName for user-facing wording and copy name verbatim into query_data_mart. Each controllable field carries its type "category", and every field carries the effective "allowedAggregations" query_data_mart may apply to it; "operators_by_category" maps each category to the filter/slice operators its fields accept — build queries from these instead of guessing. An empty allowedAggregations on a field whose "calculated" level is "metric" means the value is ALREADY computed, not that the field is unusable: select it by name in query_data_mart instead of recomputing it from other fields, and read the "usage" note carried on that field — it may also warn that a join distorts the number. Array fields are the exception: when mode is REPEATED or type or sliceType is ARRAY, the field omits category and has empty allowedAggregations. It may appear in fields, but never in filters, slices, sort, aggregations, or date_buckets. Follow get_project_context → list_contexts → context-filtered Data Mart discovery. This tool is optional in that flow: get_relevant_data_marts_by_prompt finds relevant Data Marts, and this tool adds field-level metadata for a selected Data Mart. It does not return data owners, data freshness, sample values, or actual data rows.
get_data_mart_reports
ChatGPTList the reports tied to a data mart in the active OWOX project, including each report destination, what it exports (fields, filters, slices, aggregations, date_buckets, sort, limit — in add_report/update_report vocabulary), the spreadsheet it writes to (Google Sheets), run schedules (a report can have any number of schedule triggers), and last run status. Call it before add_report to find a report that already exports what the user asks for — especially one with created_by_current_user=true — and change that one with update_report instead of creating a duplicate; reuse its spreadsheet_id when a related export should land in the same Google Sheets document.
get_project_context
ChatGPTReturns the current OWOX project selected for this MCP connection, including id, title, roles, status, and creation date. Use this tool when the user asks which project is current, active, selected, or connected. If the user asks how to change or switch projects, explain that project selection happens during OWOX authorization: disconnect and reconnect this MCP server, then sign in again and choose the desired project.
get_project_settings
ChatGPTGet settings for the current OWOX project selected for this MCP connection, including its full admin-maintained description (null when missing). Requires project viewer access.
get_relevant_data_marts_by_prompt
ChatGPTFind relevant non-draft data marts in the current OWOX project from a natural-language prompt, limited to data marts visible to the current MCP user. This is the default discovery step for a concrete analytical question when the data mart has not already been confirmed. Use it when the user asks to find, discover, or search published data marts by title, description, business meaning, schema fields, or metrics. This tool returns only data marts, not data storages or destinations, and it intentionally excludes draft data marts. Use get_project_context → list_contexts to discover business goals, then pass context_ids to restrict discovery to any selected context; omission preserves project-wide discovery within your existing access. Responses include all attached context IDs and names.
get_relevant_reports_by_prompt
ChatGPTFind existing reports in the current OWOX project from a natural-language prompt, limited to reports whose data mart and destination are visible to the current MCP user. Matches the report name first, then the data mart and destination names. Use it when the user refers to a report by name or subject and its id is not yet known — to open, rerun, change, or schedule it; each result carries the report id, its data mart and destination, and a direct link. Use get_data_mart_reports instead when the data mart is already known and you need every report with its full definition.
get_report_output_schema
ChatGPTThe columns a report's rows will carry, in the order they are projected — the names to put above the values the report delivers. Includes the columns a report synthesises (aggregated revenue | SUM, Unique Count, calculated fields), which appear in no data mart schema. Answers from the stored schema and the report config, so it reads no report data — the columns are as of the Data Mart's last schema actualization, so one added warehouse-side and not yet actualized is missing until a run or a data read picks it up. For a report that joins other data marts, resolving the join may refresh SQL-defined source views in the warehouse. This changes warehouse state and can incur warehouse costs even though the tool does not return report data rows.
get_report_run_status
ChatGPTGet the current status of a report run, identified by report_id and run_id. The run_id may come from run_report or from add_report when initial_run.status is "queued". Report runs routinely take several minutes, so keep polling while should_poll is true and stop when should_poll is false; terminal statuses are "success", "failed", "cancelled", "interrupted", and "restricted". If you can wait between tool calls, poll about every 15 seconds; otherwise call again immediately. The message field tells you what to do next, including when to warn that a run is taking longer than usual and when to treat it as stuck and stop polling. stop_reason is set only when status is still "running" but should_poll is false, such as queued_too_long or running_too_long. queued_at is when the run was created; started_at is null until execution starts, including the brief worker-claimed state before the start time is recorded. raw_status exposes the backend status, and error is populated only for failed runs.
list_contexts
ChatGPTList business contexts in the connected OWOX project, including IDs, names and complete descriptions (null when missing). Discovery flow: get_project_context → list_contexts → list_data_marts or get_relevant_data_marts_by_prompt with context_ids → get_data_mart_details_by_id. Read descriptions for business goals and Markdown links to specific Data Marts. Listing a context or following a reference never grants access to its resources; all Data Mart tools enforce existing access controls.
list_custom_connectors
ChatGPTList custom connector metadata in the connected project. The result does not include manifests. Use get_custom_connector to read the version history. To read a manifest, use get_custom_connector_version with editor access.
list_data_marts
ChatGPTList data marts available to the current OWOX project member.
list_destinations
ChatGPTList destinations in the active OWOX project to target when creating a report. Also the only way to learn the destination_id and connected Google account for a google_sheets destination just created via add_destination, since that call does not return an id synchronously — see its description. When matching that destination, never pick by createdAt/recency — someone else may create a destination at the same time, so the newest entry is not reliably the right one. Filter by connectedGoogleAccount matching who the user expected instead; if exactly one entry matches, use it, and if more than one still matches, ask the user which one they mean rather than guessing. Destinations created via add_destination start unshared: the creator can use them in their own reports right away, but other project members cannot until a human shares them (Configure destination → Sharing) — this tool does not report sharing status, so if the report is for someone other than the destination's creator, confirm with the user that it has been shared rather than assuming it.
list_project_members
ChatGPTList members of the OWOX project selected for this MCP connection, including user IDs, names, emails, roles, access scopes, and assigned Context IDs. Use returned user_id values for set_context_members; match members by name or email instead of guessing IDs. Requires project viewer access.
list_report_run_schedules
ChatGPTLists every scheduled REPORT_RUN trigger (report run schedule) in the current OWOX project that the current MCP user can see, in a single response. Each item includes trigger_id — pass it to update_report_run_schedule to modify that specific schedule or delete_report_run_schedule to remove it — plus the report and data mart it belongs to. To add another schedule for a report, call create_report_run_schedule; creating never replaces existing schedules.
publish_custom_connector
ChatGPTValidate and publish the latest draft, which immediately becomes the active version. You must be an editor with edit access to every Data Mart that follows the active version. If you do not have this access, ask a project admin or request edit access. Publishing changes future runs of Data Marts that follow the active version. Data Marts pinned to a version keep that version. Review the returned credential warnings with the user. After a conflict, call get_custom_connector again before retrying. Give the user the returned Connector Builder url to open the published connector in OWOX.
query_data_mart
ChatGPTQuery an OWOX data mart and return its data rows in a compact, header-once table, plus server-side totals computed over all matching rows (ignoring the row limit). Each call costs credits. Call get_data_mart_details_by_id first to get the data mart's exact field names and joinable/blended fields, then copy field names verbatim into fields — unless you already have that schema in context. Field names must be exact; never guess or invent them. When building the query: - Request only the fields relevant to the user's question — never request all fields. - Use limit to control how many rows come back (1–1000, default 20). There is no offset/pagination: the tool returns a bounded subset. - aggregations: SUM, COUNT, COUNT_DISTINCT, AVG, MIN, MAX, and percentiles P25/P50/P75/P95 — which of them a given field allows depends on the field's type and the data mart's per-field settings (see the matrix below). Group-by is implied by the non-aggregated fields you select. - Prefer a metric the data mart already defines: when get_data_mart_details_by_id shows a field whose "calculated" level is "metric", that field IS the quantity, computed at the grain your query asks for — list it in "fields" and read the value. Do not rebuild it by aggregating its inputs and dividing them yourself; on such a field an empty allowedAggregations means "already computed", never "unusable". - For “how many” questions, use COUNT or COUNT_DISTINCT (when the business meaning is unique entities) instead of returning raw rows and counting them yourself. Keep only dimensions the user asked to break the count by. - date_buckets: bucket a date/timestamp field by DAY/WEEK/MONTH/QUARTER/YEAR (e.g. "revenue by month"). Only date-category fields can be bucketed; time_zone applies only to types with a time-of-day component (TIMESTAMP/DATETIME — not pure DATE), and never to a Calculated Field, whose bucket must be requested without one. Which operators and aggregations fit which field type (using each field's "type" from get_data_mart_details_by_id): - number (INTEGER, FLOAT, NUMERIC, …): operators eq, neq, in, not_in, gt, gte, lt, lte, between, is_blank, is_not_blank; aggregations SUM, AVG, MIN, MAX by default; P25, P50, P75, P95 only where enabled on the field - string (STRING, VARCHAR, TEXT, …): operators eq, neq, contains, not_contains, starts_with, ends_with, in, not_in, is_blank, is_not_blank; aggregations COUNT, COUNT_DISTINCT by default; MIN, MAX only where enabled on the field - date (DATE, DATETIME, TIMESTAMP, …): operators eq, neq, in, not_in, gt, gte, lt, lte, between, is_blank, is_not_blank, before, after, in_last_n_days, in_next_n_days, this_week, last_week, this_month, this_quarter, last_quarter, this_year; aggregations MIN, MAX by default; COUNT, COUNT_DISTINCT only where enabled on the field - time (TIME): operators eq, neq, in, not_in, gt, gte, lt, lte, between, is_blank, is_not_blank, before, after; aggregations MIN, MAX by default; COUNT, COUNT_DISTINCT only where enabled on the field - boolean (BOOLEAN): operators eq, neq, is_blank, is_not_blank (eq/neq take a boolean true or false, not a string); aggregations COUNT, COUNT_DISTINCT - other (JSON, STRUCT, GEOGRAPHY, …): operators is_blank, is_not_blank; aggregations COUNT - Arrays are column-only: when a field's mode is REPEATED or its type or sliceType is ARRAY (including parameterized ARRAY types), it may appear in fields, but never in filters, slices, sort, aggregations, or date_buckets. This overrides all category rules above, including COUNT, ANY_VALUE and blank checks. A data mart can narrow a field's aggregations further ("only where enabled on the field") — get_data_mart_details_by_id returns each field's effective allowedAggregations; trust that over this table. Note COUNT/COUNT_DISTINCT are NOT available on number fields — to count rows per group, apply COUNT to a non-number field you already select that is always filled (an id field works well; COUNT skips NULLs, so a nullable field undercounts). To count UNIQUE records of a JOINED data mart (e.g. "how many distinct orders per customer"),…
run_report
ChatGPTStart an existing report by report_id and deliver fresh data to its push destination. Use this for a later rerun or when add_report returned initial_run.status="failed_to_queue". Do not call it when add_report already returned a queued run_id. Returns immediately with report_id and run_id; it does not wait for final status. Poll get_report_run_status with those ids until should_poll is false, waiting up to 15 seconds between checks when possible. Each call starts a new billed Report Run; concurrent runs are rejected as "Report is already running or pending".
save_custom_connector_draft
ChatGPTReplace the complete current draft manifest, or create the next draft if none exists. You must be an editor. Send the complete manifest, not a patch. Published versions cannot change. The active version stays active until publish_custom_connector or activate_custom_connector_version selects another version. Read the latest draft before editing to avoid overwriting another author's changes.
set_context_members
ChatGPTReplace the members assigned to a Context in the connected OWOX project. Requires a project admin. Supply user_id values from list_project_members; an empty list removes all assignments. Admin IDs are ignored because admins have project-wide access and are returned as dropped_admin_ids.
summarize_data_catalog
ChatGPTReturns a high-level summary input for the current OWOX project published Data Mart catalog so the LLM can orient the user. Use when the user asks open-ended questions like "what data is available here?", "what can I analyze?", or "where should I start?". The tool returns counts and top published Data Marts ranked by configured relationship connectivity, with shortened descriptions and basic usage metadata. It does not query actual data rows, compute data freshness, or generate a natural-language summary.
update_context_metadata
ChatGPTUpdate the name, description and/or icon of a Context in the connected OWOX project. Supply at least one metadata field. Omitted fields are preserved; null clears description or resets icon, but name must be a non-empty string. Requires a project admin.
update_custom_connector
ChatGPTUpdate the title, description, logo or documentation URL of a custom connector. You must be an editor. Omitted fields remain unchanged. Use null to clear description, logo or doc_url. The connector name cannot change. Use save_custom_connector_draft to edit the manifest. Publishing or activating a version can update display metadata from that manifest.
update_project_description
ChatGPTUpdate the description of the current OWOX project selected for this MCP connection. Requires a project admin. Provide 1–10000 characters or null to clear the description. Leading and trailing whitespace is trimmed using the existing project settings behavior.
update_report
ChatGPTUpdate an existing report: rename it, replace which data mart fields it exports, replace its output controls — filters/slices, aggregations, date_buckets, sort, limit — using the same vocabulary as query_data_mart ([] removes a control, null removes the limit), and/or — for reports with an email, slack, teams, or google_chat destination — change the message subject or body. Use it whenever the user asks to change a report that already exists — including one you created earlier in this conversation ("add a filter", "sort by revenue", "rename it") — instead of creating another report with add_report. Provide at least one change; anything not provided stays unchanged. Returns the report as it is after the update, and by default re-runs a Google Sheets report when the export changed (run.status="queued" — poll get_report_run_status), so the sheet shows the new definition; email, Slack, Teams, and Google Chat reports are re-sent only with run_immediately=true.
update_report_run_schedule
ChatGPTUpdates one existing report run schedule identified by trigger_id (get it from list_report_run_schedules). This changes cron_expression, and optionally time_zone and is_active; it does not change the report target and does not create another schedule. Changing or disabling a schedule can skip report deliveries, and missed runs are not replayed when the schedule is restored. To add another schedule for the same report, call create_report_run_schedule instead. time_zone must be a valid IANA timezone (e.g. "Europe/Kyiv"); if omitted, the schedule keeps its current timezone. If is_active is omitted, the schedule keeps its current active state.
add_destination
Claudeadd_report
Claudecreate_report_run_schedule
Claudedelete_report
Claudedelete_report_run_schedule
Claudeget_data_mart_details_by_id
Claudeget_data_mart_reports
Claudeget_project_context
Claudeget_relevant_data_marts_by_prompt
Claudeget_relevant_reports_by_prompt
Claudeget_report_output_schema
Claudeget_report_run_status
Claudelist_contexts
Claudelist_data_marts
Claudelist_destinations
Claudelist_report_run_schedules
Claudequery_data_mart
Clauderun_report
Claudesummarize_data_catalog
Claudeupdate_report
Claudeupdate_report_run_schedule
Claude
