MCP App Store
by KeenEthics
Instrumentl icon

Instrumentl MCP Server for Claude and ChatGPT

By Instrumentl

Overview

Instrumentl integration for nonprofits. Make Instrumentl a native part of your AI workflow — an intelligent partner that helps you find, win, and manage grants faster, directly in Claude.

How to connect

  1. Claude: Open the Instrumentl listing in the Claude connectors directory and choose Connect. Claude listing Instrumentl exposes 6 tools here.
  2. ChatGPT: Open the Instrumentl listing in the ChatGPT app directory and choose Connect. ChatGPT listing Instrumentl exposes 35 tools here.

Tools

bulk_destroy_expenses

ChatGPT
Delete one or more expenses by their API IDs (e.g. exp_...). Best-effort: critically required expenses linked to external systems (QuickBooks, Sage Intacct, etc.) cannot be hard-deleted and are returned in the failed array with a reason; other expenses in the same call are still deleted. The response shape is: { deleted_ids: ["exp_...", ...], failed: [{id: "exp_...", reason: "..."}, ...] } Possible failure reasons: - "not_found": the id doesn't exist or belongs to a different account - "not_authorized": the caller lacks permission to delete this expense - "linked_to_external_system": the expense is mirrored from an external integration and must be removed there first

bulk_update_expenses

ChatGPT
Update one or more expenses by their API IDs (e.g. exp_...). Best-effort: expenses that don't exist, belong to a different account, or that the caller lacks permission to modify are returned in the failed array with a reason; other expenses in the same call are still updated. Currently the only supported update is toggling whether an expense is ignored. Ignored expenses are excluded from budget totals but kept on the account for reference. Pass ignored: true to mark expenses as ignored, or ignored: false to restore them. The response shape is: { updated_ids: ["exp_...", ...], failed: [{id: "exp_...", reason: "..."}, ...] } Possible failure reasons: - "not_found": the id doesn't exist or belongs to a different account - "not_authorized": the caller lacks permission to update this expense

create_expenses

ChatGPT
Add one or more expenses to a grant's budget. Each expense attaches to a specific expense category (an ec_... API ID) within a saved grant (an save_... API ID); call list_budgets first to find the right category and its remaining budget. Amounts are integer cents (e.g. 12500 = $125.00). Best-effort: each expense is created independently. Items that fail (unknown or forbidden grant/category, validation errors) are returned in the failed array — each carries its input fields and a reason — while the rest are still created. Pass dry_run: true to preview the budget impact WITHOUT creating anything. The preview reports, per category, the projected remaining budget, whether it would be overspent, and any expenses that already exist in that category — useful to catch a planned expense the user may want to update rather than duplicate. Prefer a dry run first whenever an expense might exceed a budget or already exist. To update or remove existing expenses, use bulk_update_expenses or bulk_destroy_expenses instead of creating new ones. Create response shape: { created_ids: ["exp_...", ...], failed: [{index, reason, saved_grant_id, expense_category_id, amount_cents, errors?}, ...], budget_impact: [{expense_category_id, category_name, remaining_cents, overspent}, ...] } Dry-run response shape: { projected: [{saved_grant_id, expense_category_id, category_name, budgeted_cents, current_remaining_cents, added_cents, projected_remaining_cents, overspent, existing_in_category, existing_in_category_has_more}, ...], failed: [...] } Possible failure reasons: - "not_found": the grant or category doesn't exist or belongs to a different account - "not_authorized": the caller lacks permission to add to this grant - "invalid": the expense failed validation (details in errors)

create_folders

ChatGPT
Create Document Library folders. Pass up to 5 entries in folders. - name: The new folder's name. - parent_folder_id: (optional) API ID for the new folder's parent folder. Omit it, or pass null, to create the folder at the top level. Folder name rules: - 1 to 255 characters. - Only letters, numbers, spaces, and the following characters: - _ . ( ) - Must be unique within the parent folder. Notes: - Folders can be nested at most 10 levels deep. - To create more than 5 folders at once, call this tool again. - Use list_folders to find parent folder ids.

decide_funder_matches

ChatGPT
Save or hide ("not interested") one or more of a project's Funder Matches (from list_project_funder_matches), each with its own action. A Funder Match is a whole funder, so this saves the funder's grant to the project's tracker, or hides it in the project, creating the account's custom grant for the funder if it does not exist yet. Afterwards list_project_funder_matches reports a saved one's decision as "saved", and a hidden one's as "hidden" unless it was already saved (see below). Give an entry notes to record why the user saved or hid it; they are stored as the SavedGrant's notes. Pass the user's own words, not a summary of your reasoning. Null means no note. Best-effort: a funder match that can't be decided is returned in failed with a reason, and the others are still decided. The response shape is: { saved_grants: [SavedGrant, ...], failed: [{id: "fdmatch_...", reason: "...", errors: [...]}, ...] } Possible failure reasons: - "not_found": the id is not one of this project's funder matches - "invalid": the SavedGrant could not be created or hidden; errors says why - "not_authorized": the user may not change this funder match's SavedGrant - "already_saved": "save" on a funder match the project has already saved; nothing changed An unknown project, or one the user cannot see, fails the whole call before anything is decided. "save" saves the funder's grant to the project. It only works on a funder match that is undecided or hidden, so retrying a call does not save a funder twice. "hide" on a funder match with an unsaved draft in the project hides that draft, adding any notes to its notes; otherwise it creates a hidden one. "hide" does not remove a funder match that is already saved to the tracker: that SavedGrant stays saved, and list_project_funder_matches still reports the match as "saved". Tell the user so rather than saying it was hidden.

delete_documents

ChatGPT
Delete one or more documents (doc_...) and document links (encryptedcred_...) from the account's Document Library by their API IDs. Pass at least one of documents or document_links. Best-effort: items that can't be deleted are returned in the failed array with a reason, other items in the same call can still be deleted. Deleting is permanent from the user's point of view, so confirm with the user before calling this tool. The response shape is: { deleted_ids: ["doc_...", "encryptedcred_...", ...], failed: [{id: "doc_...", reason: "..."}, ...] } Possible failure reasons: - "not_found": the id doesn't exist, was already deleted, or belongs to a different account - "not_authorized": the caller lacks permission to delete this item Users usually refer to documents by name, so use list_documents to find document ids.

generate_snippets

ChatGPT
Start snippet/answer generation for a grant application. The grant must be saved in the user's tracker. Use list_saved_grants to find the saved grant and pass it as saved_grant_id. The saved grant must: - Be in the "Planned" status. If not, update its status using update_saved_grant. - Have a current or upcoming funding cycle (rolling grants do not need funding cycles) with a live application form. Use request_application_form first if no live form exists. Use list_documents to find relevant Documents you wish to use for snippet generation. Relevant documents include past grant application proposals and any others that include relevant context for this application. Pass them in as documents. - If no documents are provided by the user, ask. Do not call this tool until the user specifies at least 1 document. user_filters are optional details that help tailor the generated answers: - contact_first_name. - type_of_request: "programmatic" or "operational". - This pairs with either program_name (programmatic) or organization_name (operational). Omit user_filters entirely to leave previously saved filters unchanged, or pass it to overwrite them. Snippet generation is asynchronous. This tool only starts the process, so you can use list_snippets to check the status of the snippet generation. It takes 3 minutes on average for snippet generation to complete, poll no more than every 30 seconds starting at 3 minutes Call this tool again, with any updated documents or user filters, to re-generate the snippets for the saved grant.

get_current_account

ChatGPT
Retrieve the Instrumentl account the caller is authorized to act in.

hide_saved_grant

ChatGPT
Hide a previously-saved grant by marking its SavedGrant as no longer saved (saved: false, hidden: true). Pass the SavedGrant's id (e.g. save_...). This is reversible and non-destructive: the SavedGrant and any application data attached to it (submission goals, tasks, expenses, etc.) are preserved, and the grant can be saved again later. To find the right saved_grant_id, list the project's saved grants (list_project_matches filtered by saved status, or look up via list_project_matches's saved filter).

list_application_questions

ChatGPT
List the grant application form questions. Pass the grant's id from list_grants or search_grants as grant_id. If a user gives a grant name, resolve it with one of those tools first. Never guess an id. A grant has 1 application form per funding cycle. By default this returns the form of the most recent funding cycle; pass funding_cycle_id (from the grant's funding_cycles in list_grants) to pick another cycle. meta.funding_cycle_id names the cycle returned; null means the form is not tied to a cycle. Each item returns the question text, and addition information about the question like section, validation etc. Respect these limits when drafting answers. An empty list means the grant has no live application form. Use the request_application_form tool to request that the form be built, if it is available to you, or request it through the Instrumentl UI. Each account can make up to 30 application question retrievals through MCP per calendar month, resetting on the first at 00:00 UTC. Calls that return an empty list do not count toward this limit.

list_budgets

ChatGPT
List the current user's budgets — one per saved grant that has a budget set up — to decide which budget an expense belongs to. Saved grants with no expense categories are omitted (unless requested by saved_grant_ids). Optionally narrow the results (filters compose with AND; omit all to list every budget). The user usually refers to a budget by name rather than id: - grant_name: the grant's name (case-insensitive substring) — use when the user names a grant - project_name: the project's title (case-insensitive substring) — disambiguates when grant names repeat - saved_grant_ids: budget ids (saved grant ids, prefix "save_") for exact budgets - transaction_date: an expense date (YYYY-MM-DD) — returns budgets whose award period covers it Each budget's "id" is its saved grant id (prefix "save_") for use with other saved-grant tools, plus grant_name and project_title to identify it. A budget contains budget_phases (each phase is a time window such as a grant year), and each phase contains expense_categories nested as a tree (child_categories). All amounts are integer cents (amount_currency holds the currency): - amount_cents: budgeted amount - actual_cents: spent so far (excludes planned and ignored expenses) - planned_cents: planned but not yet actual - remaining_cents: amount_cents - actual_cents - planned_cents (negative means over budget) Category amounts roll up the whole subtree, so a parent category's totals include its children's. To place an expense, match it to a category by name and prefer a budget/category whose remaining_cents can cover it.

list_custom_field_definitions

ChatGPT
List the account's custom field definitions — the extra fields this organization has added to its saved grants and funders. Call this first whenever the user names a field that is not a built-in one ("Priority", "Program Area", "Internal Owner"). It is the only way to resolve such a name to a field and to learn what values that field can hold. Then pass include_custom_fields: true to list_saved_grants or list_funders to read the values themselves. Each definition returns: - name: what the user calls the field - attached_to: which record the field hangs off (SavedGrant, Funder) - value_type: one of string, text, date, amount, numeric, enum, multiselect, link - options: for enum and multiselect fields, the allowed choices, each with an option_key (stored), an option_value (shown to people) and a display_order Values read back from list_saved_grants and list_funders are option_value labels, not option_keys, so compare them against option_value. A multiselect value is those labels joined with ", ". Filters: - attached_to: SavedGrant, Funder — narrows to fields on saved grants or on funders With no filters, returns the account's custom fields a page at a time — page_size defaults to 20. If meta.has_more is true there are more definitions; page with the cursor before concluding a field does not exist.

list_documents

ChatGPT
List the documents in the account's Document Library. Filter with search (search over title, file name, summary, extracted text and project title), purposes, or file extensions.

list_expenses

ChatGPT
List the current user's expenses. At least one filter must be provided: - saved_grant_id: a SavedGrant api_id (prefix "sgrt_") - expense_ids: an array of Expense api_ids - project_name: a project title (case-insensitive substring); conditionally joins projects - grant_name: a grant name (case-insensitive substring); conditionally joins grants Filters compose with AND. project_name and/or grant_name resolve to the user's matching saved grants and return all expenses across them.

list_folders

ChatGPT
List the folders in the account's Document Library. Filter with search to filter by folder name.

list_funder_contacts

ChatGPT
List all Funder Contacts

list_funders

ChatGPT
List all Funders

list_grants

ChatGPT
List all grants. This API will only return grants that match one of the following: 1. are custom for your user (created via a spreadsheet upload or custom grant form) 2. saved to a project 3. hidden from a project 4. hidden account-wide.

list_programs

ChatGPT
List the account's active programs: the internal programs or departments (e.g. "Youth", "Arts Education") that saved grants are assigned to in the tracker. Call this to resolve a program the user names to its id (prefix "prog_"). Then pass that id as program_id to list_saved_grants to find the grants in that program, or in add_program_ids / remove_program_ids to update_saved_grant to change a grant's programs. Returns the programs a page at a time; page_size defaults to 20. If meta.has_more is true, page with the cursor before concluding a program does not exist.

list_project_funder_matches

ChatGPT
List Instrumentl's recommended funders (Funder Matches) for a Project. A Funder Match is a whole funder, not one grant; for recommended grants, use list_project_matches. Each Funder Match has a decision: "saved" when the user saved a grant from that funder to this project, "hidden" when they hid one ("Not interested") from this project or from all projects, and "undecided" otherwise. Pass its ein to list_funders for the funder's details.

list_project_matches

ChatGPT
List Instrumentl's recommended Grants (Matches) from the public catalog for a Project. A Match is a suggested funder/grant the user has not yet decided on; it is separate from the user's tracker, which is a view of saved grants. Before calling this tool, disambiguate with the user when the wording could go either way. Users routinely say "my grants/matches/opportunities (for my project X)" to mean entries already in their tracker (SavedGrants → list_saved_grants), and other times to mean fresh recommendations from the catalog (Matches → this tool). Ask a short clarifying question, e.g.: "Do you mean grants/matches already saved in your tracker, or new recommendations Instrumentl has surfaced for this project?" Use this tool only after confirming the user wants recommendations; otherwise call list_saved_grants (it accepts project_name or project_id). Filters: - project_id: a Project api_id (prefix "proj_") to scope recommendations to that project - match_ids: array of Match api_ids

list_projects

ChatGPT
List all projects associated with the current account

list_saved_grants

ChatGPT
List the user's SavedGrants — entries already in their tracker. A SavedGrant is the user's record of pursuing a Grant for a specific Project; an "awarded" SavedGrant is one with status "funding_awarded" or "closed". Each SavedGrant has a status (the machine value — use it for the statuses filter and for update_saved_grant) and a status_label (the label the user sees in their tracker). Always use status_label when describing a status to the user; never show them the raw status value. Before calling, disambiguate when the wording is ambiguous; ask a single clarifying question rather than guessing. The most common confusion is between SavedGrants (already in the tracker) and Matches (new recommendations from the public catalog). A good clarifier: "Do you mean grants/matches already in your tracker, or new recommendations Instrumentl has surfaced for this project?" - "my grant(s)", "my match(es)", "my opportunity/opportunities", "grants for my project X", "what have I saved/tracked": almost always SavedGrants already in the tracker → THIS tool. If the phrasing could plausibly mean "new recommendations" instead, confirm with the user first; use list_project_matches only after they confirm they want recommendations. - "awards", "current grants", or bare "grants" in an award/funding context: awarded SavedGrants → THIS tool with awarded: true (matches both "Awarded - Active" and "Awarded - Closed"). For only currently-active awards, pass statuses: ["funding_awarded"] instead. - "find grants", "search grants", "what grants are available": the public Grant catalog → use list_grants. - Bare "grants" with no "my" and no award context: ambiguous — ask first. Filters (compose with AND): - saved_grant_id: a SavedGrant api_id (prefix "save_") — returns just that one - project_id / grant_id / funder_id: api_ids to scope by the related record - statuses: array of SavedGrant status values. Map the tracker label the user names to its value: researching = "Researching", planned = "Planned", loi_in_progress = "LOI In Progress", loi_submitted = "LOI Submitted", started = "Application In Progress", submitted = "Application Submitted", funding_awarded = "Awarded - Active", closed = "Awarded - Closed", declined = "Declined", abandoned = "Abandoned" - awarded: true restricts to awarded SavedGrants; false excludes them - award_year: integer fiscal year for the award period - project_name: case-insensitive substring on the project title (use when the user names a project) - grant_name: case-insensitive substring on the underlying grant's name (use when the user names a grant) - submission_goal_gte / submission_goal_lte: ISO dates (YYYY-MM-DD); keeps saved grants with a submission goal date in the range (either bound may be omitted) - submission_goal_submitted: false keeps saved grants with a goal not yet marked submitted (no submitted_at); true keeps those with a goal marked submitted. When combined with the date range, the same goal must match both Submission goals: each saved grant carries a submission_goals array holding the goals for the funding cycle it currently tracks (goals left on other cycles' deadlines are omitted). Each entry's submission_goal is the date the user plans to submit (their target/goal date for that deadline) and submitted_at is when they actually submitted; deadline_id ties it to the funder deadline it was set against, and deadline_name says which deadline of the cycle it is (letter_of_inquiry, pre_proposal, full_proposal, or null when unnamed or not tied to a funder deadline). Use these to answer "when are we planning to submit" or "what are our submission goals" questions — do not infer them from the Grant's funding cycles. Deadline questions ("what's due this month?", "what are we submitting next quarter?"): pass the date range plus statuses limited to the in-progress ones (planned, started, loi_in_progress, loi_submitted), and add submission_goal_submitted: false to drop goals already marked submitted (e.g. the LOI on an loi_submitted grant). Rely on status first: submitted_at is often left bla…

list_snippets

ChatGPT
List the AI-generated answer snippets of a grant application, grouped by application question. Pass the application_id returned by generate_snippets. Snippets are generated asynchronously: meta.status is the application's generation status (in_progress means more snippets may still arrive; completed means the run has finished). Only questions that already have at least one snippet are returned, so an empty list while in_progress just means nothing has been generated yet — check again later rather than restarting generation. Each snippet carries the answer text and its sources: the documents, grants or funders it was drawn from. An empty sources list means the answer was synthesized from the application's documents without a specific citation. Pass question_ids (the ids from list_application_questions) to only return snippets for those questions.

list_tasks

ChatGPT
List the user's Tasks (also called custom grant deadlines). A Task belongs to a SavedGrant in the user's tracker and can have an assignee, a nominator, a creator, and (when done) a completer. DISAMBIGUATE before filtering by a person. The tool exposes four separate people filters — assignee, nominator, created_by, completed_by — because each captures a different relationship and they AND-compose, so picking the wrong one returns wrong results. When the user names a person without a clear role ("Sarah's tasks", "tasks for Sarah", "what is Sarah working on"), ask which they mean before calling. A good single clarifier: "Do you mean tasks assigned to Sarah, tasks she created, tasks she completed, or tasks she nominated (handed off)?" Common phrasings → likely role: - "my tasks", "Sarah's tasks", "tasks for Sarah", "what is Sarah working on": almost always assignee — confirm and proceed. - "tasks Sarah added/made/wrote": created_by. - "tasks Sarah finished/completed/closed out": completed_by (also implies done). - "tasks Sarah handed off / reassigned / passed to someone else": nominator. If unclear, ask before guessing. Each people filter matches first name, last name, OR email (case-insensitive substring), so the user need not say which form they remember. Other filters (compose with AND): - saved_grant_id / project_id: api_ids — use when you already have the id (e.g. from another tool call) - project_name / grant_name / funder_name: case-insensitive substrings — use when the user names the entity - assignee_id / nominator_id: user api_ids — for an exact person rather than a name search - is_done: true returns completed tasks; false returns open tasks ("show open tasks" is the most common ask) - past_due: true returns overdue, not-done tasks; false excludes them - unassigned: true returns tasks with no assignee (use for "tasks nobody owns") - kinds: array of task kinds (full_proposal, report, general, letter_of_inquiry, cultivation, application, payment_request, contract_agreement, site_visit, communications, event, other) - deadline_gte / deadline_lte: ISO dates; deadline_gte INCLUDES tasks with no deadline, deadline_lte does not Call with no filters to list every task in the user's tracker.

list_users

ChatGPT
List the users (teammates) on the current account. Use this when the user references a teammate by name and you need their id to pass into another tool — assignee_id / nominator_id on ListTasks, user_id on ListProjects, owner / created-by filters on saved grants, etc. All those tools key off a user api_id (user_...), not an email or name. Filters (compose with AND): - search: case-insensitive substring match across first_name, last_name, and email — the workhorse for resolving "John Williams", "john@", or a partial name to a user - email: exact-match email lookup — use only when you already have the full email With no filters, returns every user on the account.

request_application_form

ChatGPT
Request an application form for a grant already saved in the user's tracker, or check the status of an existing request. Use list_saved_grants to find the SavedGrant and pass its id as saved_grant_id. If the grant has not been saved yet, call save_match first and use the SavedGrant id it returns. Never guess an id. Do not use this tool for custom grants. Direct the user to request a custom grant's application form in the Instrumentl UI. The funding cycle is selected automatically: the cycle chosen on the saved grant if its deadline is still in the future, otherwise the grant's next upcoming cycle. Rolling grants have no funding cycle and need nothing extra. The call fails if the grant is not rolling and has no upcoming cycle, for example an opportunity whose cycles have all closed. This tool is idempotent. Call it again with the same arguments to check the current status. Status meanings: - not_started: no request has been made - in_progress: a request has been made - live: the application is ready to start - cannot_be_built: the application form cannot be built Each account can make up to 10 application form requests through MCP per calendar month, resetting on the first at 00:00 UTC. Checking an existing request's status or accessing an already-live form does not count toward this limit.

save_match

ChatGPT
Save a grant match to a project. Defaults to saving to the project the match belongs to; pass target_project_id to save the grant to a different project in the same account. Pass hide: true to instead hide ("not interested") the match, so it no longer appears in the project's matches. This is reversible in the Instrumentl app. target_project_id is ignored when hiding. Each call creates a new SavedGrant. To remove a grant you previously saved, use the hide_saved_grant tool with the SavedGrant id returned here.

submit_feedback

ChatGPT
Send a feedback message from the user to the Instrumentl engineering team. Call this only when one of the following is clearly true: - The user has explicitly asked to report a bug, request a feature, or send feedback to the team. - You have already attempted to help with the user's actual task, and the user is still blocked or has expressed unresolved frustration that cannot be solved inside this conversation. DO NOT call this: - Proactively, on the first sign of frustration. Try to help first. - When the user is merely unsure how to do something -- answer the question instead. - More than once per conversation, unless the user explicitly asks to send another message. Before calling, do both of these with the user (do not guess either): 1. Confirm the wording of the message -- the team only sees what is passed here. 2. Ask which category best fits (bug / feature_request / complaint / other). Do not infer the category yourself unless the user has clearly stated it. The submission is delivered asynchronously to a private Slack channel monitored by engineering and product. There is no follow-up channel here, so do not promise a reply on a specific timeline.

update_documents

ChatGPT
Rename and/or move documents (doc_...) and document links (encryptedcred_...) in the account's Document Library. Pass up to 100 entries in documents and document_links combined. - documents: document_id, plus an optional title and/or folder_id. - document_links: document_link_id, plus an optional name and/or folder_id. Notes: - Omit a field or pass null to keep it unchanged. - Use folder_id: "root" to move an item to the root ("All Files"). - Use an empty string title: "" or name: "" to clear it. - Best-effort: entries that can't be updated are returned in the failed array with a reason, the rest can still be updated. The response shape is: { updated_ids: ["doc_...", "encryptedcred_...", ...], failed: [{id: "doc_...", reason: "..."}, ...] } Possible failure reasons: - "not_found": the id doesn't exist or belongs to a different account - "not_authorized": the caller lacks permission to update this item - "folder_not_found": the folder_id isn't "root" or a folder ID, doesn't exist, or belongs to a different account - "duplicate": the id appears more than once; none of its entries are applied Use list_documents to find document ids and list_folders to find folder ids.

update_folders

ChatGPT
Rename and/or move Document Library folders. Pass up to 5 entries in folders. - folder_id: API ID (prefixed folder_) for a folder being updated. - name: (optional) A new name for the folder. Omit to keep it unchanged. - parent_folder_id: (optional) API ID (prefixed folder_) for the folder's new parent folder. Omit to keep it unchanged. Use parent_folder_id: null to move the folder to the root. Notes: - A moved folder's subfolders, documents and credentials move with it. - This tool call is all-or-nothing. If any entry fails, nothing is changed. - To update more than 5 folders at once, call this tool again. - An entry with neither the name nor parent_folder_id param is ignored. Use list_folders to find folder ids.

update_saved_grant

ChatGPT
Update fields on a saved (tracked) grant. Pass the SavedGrant's id (e.g. save_...) plus only the fields you want to change - omitted fields are left untouched. Updatable fields: - status: where the grant is in the pipeline. Users name it by its tracker label (e.g. "Application Submitted"); send the matching value (e.g. submitted). The response's status_label is what to show the user. - notes: free-form notes about the opportunity. - amount_requested / amount_awarded: dollar amounts. - year: fiscal year the grant is tracked under. - notified_at, award_period_start_date, award_period_end_date: dates relevant once a grant is awarded. - owner_id: the User (user_...) to make responsible for the grant, or null to clear the owner. - project_id: move the grant to a different project (proj_...). Notes: - Setting status to researching clears the requested amount and submission goals, matching the app's behavior. - To stop tracking a grant, use hide_saved_grant instead. Use list_saved_grants to find the saved_grant_id.

upload_documents

ChatGPT
Upload one or more documents to the account's document library, optionally attaching them to saved grants and tasks. Each document requires data_base64 containing strict base64-encoded file contents (without a data-URL prefix) and filename including its extension. title is an optional custom title. If you want to associate any of the documents with saved grants, use the list_saved_grants tool to find saved grants and pass their id values in each document's saved_grant_ids. If you want to attach any of the documents to tasks, use the list_tasks tool to find tasks and pass their id values in each document's task_ids. IMPORTANT: The document will also be associated with each task's saved grant. Each document may include a folder_id to select its destination folder. Omit it on a document to upload that file to the library root. Allowed filename extensions (case-insensitive): pdf, docx, doc, png, jpg, jpeg, csv, xlsx, xls. Upload limits are 25 MB per file and 30 MB total, measured using decoded file sizes. Each document is uploaded independently. If one fails (eg: an unsupported file type, a file over the size limit, or a saved grant, task, or folder that can't be found or accessed), it is marked failed and the rest can still upload. Only a batch over the total size limit rejects the whole request. This tool is not idempotent. Repeating a successful upload creates another document; do not retry successful items. Each document returns its original input filename, a status, and an errors array. The returned filename matches the input even if storage sanitizes it. Status meanings: - success: the file and requested associations were saved, errors is empty. - failed: the document could not be uploaded, errors contains an explanation.

upsert_budget_versions

ChatGPT
Draft a budget version for a saved (tracked) grant. A budget version is made of phases (time windows such as grant years), each holding a tree of expense categories up to 3 levels deep, with optional splits across funding sources. All amounts are integer cents (12500 = $125.00). This only drafts. The result is a DRAFT budget version that the user reviews and activates in the Instrumentl app (the grant's Financials page). Nothing about the grant's current active budget, its expenses, or its funding sources changes, and no expense categories or budget phases are created until activation. A budget version can never be activated through this tool; only a person can activate one, in the app. Create vs update: - Omit budget_version_id to create a new draft budget version. - Pass the bv_... id of an existing DRAFT budget version on the same grant to replace its contents. Its name and description are kept unless you pass new ones. Active or archived versions cannot be replaced; create a new draft instead. What is derived for you: - A category's amount_in_cents is summed from its subcategories when omitted, or from its funding sources when they carry amounts. - A category's funding sources are rolled up from its subcategories when omitted. - funding_source_names is collected from the categories when omitted. In the response it is empty for a single-source budget, because the app only shows a funding-source split when there is more than one source. - Phase and category ids in the response are draft-local identifiers, not bp_ or ec_ API ids; those only exist once the version is activated. Requirements and tips: - The account must have the Budget Versioning feature. - The grant can be in any status, including grants that are not yet awarded. - Use list_saved_grants to find saved_grant_id. list_budgets lists each grant's budget_versions, including drafts with their draft_phases; read a draft there before replacing it, and take budget_version_id from its "id". - Phase names must be unique, and sibling category names must be unique. - Dates are ISO 8601 (YYYY-MM-DD); end_date must be after start_date.

upsert_tasks

ChatGPT
Create new tasks and/or update existing tasks in a single best-effort call. Each row in tasks is either: - { "op": "create", "saved_grant_id": "save_...", "kind": "...", ...optional fields } - { "op": "update", "id": "task_...", ...fields to change } Rows are processed independently — a failed row does not roll back the others. Use op: "create" to add a task to a SavedGrant. saved_grant_id and kind are required; the calling user becomes the creator and nominator. Use op: "update" to change an existing task. Only id is required; pass any subset of mutable fields. Pass done_at as a timestamp to mark the task complete, or null to reopen it. Available kinds: full_proposal, report, general, letter_of_inquiry, cultivation. Resolving a user for assignee_user_id or notify_user_ids: these must be user_... API IDs. If the user names someone by first name, last name, or email, call list_users to resolve the API ID first. Do not try to find users via list_tasks people filters — those only surface users who already appear on a task, not every member of the account. The response shape is: { "results": [ { "index": 0, "op": "create", "status": "ok", "task": { ... } }, { "index": 1, "op": "update", "status": "failed", "reason": "not_found" } ], "created_count": N, "updated_count": N, "failed_count": N } Each result's index matches the input row at the same position. Possible failure reasons: - "not_found": task id doesn't exist or belongs to a different account (update) - "saved_grant_not_found": saved_grant_id doesn't exist or belongs to a different account (create) - "user_not_found": assignee_user_id or notify_user_ids contains a user not in this account - "not_authorized": the caller lacks permission for this row - "invalid": validation failed; see errors

get_current_account

Claude

get_grant

Claude

get_match

Claude

list_grants

Claude

list_project_matches

Claude

list_projects

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/instrumentl"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/instrumentl)