MCP App Store
by KeenEthics
Productive icon

Productive MCP Server for Claude and ChatGPT

By Productive

Overview

Productive is the agency management platform that connects sales, projects, resourcing, time tracking, budgeting, and invoicing in one place. This connector gives Claude secure access to your Productive workspace so you can get answers and get work done without switching tabs. Ask about your open tasks, log time against a project, check where a budget stands, or draft a page. Claude works with your live data and respects the same permissions you have in the app. What you can do: Project management. Create and update projects, tasks, and subtasks, including assignees, due dates, statuses, and dependencies. Time tracking. Log, update, and delete time entries, start and stop timers, and manage timesheet submissions. Budgeting and finances. Read and create invoices, expenses, payments, and purchase orders, and check budget and margin status. Sales CRM. Access and update your deals pipeline, companies, contacts, and proposals. Resourcing. View team bookings, time off, and service allocations. People and organization. Look up people, teams, roles, and reporting structure. Docs. Create, edit, and delete pages and comments. Reporting. Query reports across budgets, time, financials, projects, and people. Access and security. Each user connects individually with their own Productive login, and the connection authorizes access only to that account. One connection covers one Productive organization at a time. A separate Sandbox server is available for testing without touching live data.

How to connect

  1. Claude: Open the Productive listing in the Claude connectors directory and choose Connect. Claude listing Productive exposes 17 tools here.
  2. ChatGPT: Open the Productive listing in the ChatGPT app directory and choose Connect. ChatGPT listing Productive exposes 17 tools here.

Tools

create_resource

ChatGPT
Create one or more records of a given resource type. Use describe_resource with include: ["fields"] first to learn required and optional fields. Provide a single-item array to create one record, or multiple items for bulk creation. Use productive_domain to discover all available resource types.

delete_resource

ChatGPT
Delete one or more records of a given resource type. Provide a single-item array to delete one record, or multiple items for bulk deletion.

describe_report

ChatGPT
Describe the available fields, groups, filters, and custom fields for a report type. Inline tags on each field convey extra capability: "(formulable)" — usable in formula expressions "(sortable)" — usable as a sort_by value (prefix "-" for descending) "(sortable: <key>)" — sortable but only via the named key (the API sort key differs from the field key) "(list)" on a filter row — that filter accepts a list of values; rows without it accept a single scalar value A date-period group key carries a required bucket suffix, shown inline as "<key>:{day|week|month|quarter|year}" — pick exactly one bucket (e.g. "date:month") for both group_by and sort_by; the bare key is not a valid group/sort value. Call this before query_report to understand what configuration is available. By default, includable relationships are listed compactly (name and type only). To see available attributes for include_fields, pass include_fields_for with relationship keys to expand.

describe_resource

ChatGPT
Describe a resource type in the Productive domain — its purpose, available operations, and pointers to every detail area. Call this to learn how a resource works before querying, creating, or updating records. Without options, returns a compact overview that includes a short hint for each detail area that exists (fields, relationship filters, custom fields, actions). Pass include to expand any of those areas: "fields" for the full field schema (types, flags, filter operators, sort, search), "relationship_filters" for the dot-notation filter list, "custom_field_schemas" for org-specific custom field metadata, "action_schemas" for full action input schemas. Use productive_domain to discover all available resource types.

get_current_person_and_organization

ChatGPT
Load the current user's identity (name, email, role) and their organization (currency, timezone, services offered). Call this early to resolve "me"/"I"/"my" — who you're talking to and what kind of organization they work in.

load_resource

ChatGPT
Load a single resource by ID. Returns primary attributes only by default. Use include_fields to request relationship attributes (e.g. "assignee.first_name", "project.name"). Large responses are replaced by a slim handle stub: items is a single {type, id} pointer (not the full record). The stub envelope carries output_type: "json" so query_output knows to route through jq. Call query_output(output_id, jq_expression=<jq>) against the handle to read fields. The store envelope is {items: [{id, type, fields}], included?}; fields is keyed by the field's param from describe_resource (e.g. .items[0].fields.title). Relationship values under fields are {type, id} objects (NOT JSON:API .relationships.<name>.data). See query_output for the supported jq subset.

load_skills

ChatGPT
Load full instructions and available actions for one or more skills by id. Skills are specialized domain workflows (e.g. automation-builder), domain guides (e.g. task-creation), or user-authored skills defined by the organization. Call this with every skill id whose description matches what the user needs — up to 5 per call. The response includes each skill's instructions and any actions you can call via perform_action. Prefer one batched call over multiple single-id calls when several skills are relevant.

perform_action

ChatGPT
Execute a registered action by its globally-unique slug (e.g. "send_email", "archive_email_thread", "validate_automation"). describe_resource lists each resource's available actions and their signatures in its default overview; pass include: ["action_schemas"] for full input schemas.

productive_domain

ChatGPT
Productive domain reference — all resource types, tool usage patterns, and search strategies. Start here if you are unfamiliar with this server.

query_report

ChatGPT
Query a report endpoint to fetch aggregated data. Returns raw report data grouped, filtered, and sorted as specified. Always call describe_report first to understand available fields, groups, filters, and sorts. Slicing uses limit (default 30, max 200) and offset (default 0; must be a multiple of limit). Three call shapes (mutually exclusive): - Fresh query: {report_type, name, group_by?, filters?, formulas?, sort_by?, currency_variant?, include_fields?, display_fields?, report_layout?, chart_type?, limit?, offset?} — issues a new query and returns a query_id you can use to continue it. - Continuation: {query_id, offset, limit?} — the full report config (report_type, name, group_by, filters, formulas, sort_by, currency_variant, include_fields, display_fields, report_layout, chart_type) is pinned from the original call. offset is required — pass the next_offset from the previous response. - Saved report: {report_id, limit?, offset?} — runs the report as saved, so the data matches the report the user sees. The response includes the report's config in query form; adjust it in a fresh query for a modified question. An error carries saved_report_ran: false; a fresh query's results are not this report's data.

query_resources

ChatGPT
Query resources of a given type with structured filters, sorting, and slicing. Use describe_resource with include: ["fields"] first to learn available filter fields, operators, and their types. Slicing uses limit (default 20, max 200) and offset (default 0; must be a multiple of limit). For top-N queries pair sort + limit (e.g., sort=["-created_at"], limit=10). Two call shapes (mutually exclusive): - Fresh query: {resource_type, filters?, sort?, limit?, offset?, include_fields?} — issues a new query and returns a query_id you can use to continue it. - Continuation: {query_id, offset, limit?} — resource_type, filters, sort, and include_fields are pinned from the original call. offset is required — pass the next_offset from the previous response. Use productive_domain to discover all available resource types.

read_file_from_url

ChatGPT
Downloads and reads a file from a URL. Returns extracted text for PDFs, decoded text for text-family files (txt, md, json, csv, tsv, xml, log, rtf, svg, html), extracted body text for DOCX, per-sheet cell text for XLSX (computed formula values), per-slide text with speaker notes for PPTX, inline vision for images (png, jpeg, gif, webp, heic/heif), and format-specific guidance for unsupported types. Large text outputs are truncated; the result notes how much was returned and that the rest cannot be retrieved. Use this for files.productive.io URLs (attachments on Productive resources like tasks, comments, deals, expenses); the tool injects the caller's auth token automatically. Also works for any public URL.

search_help

ChatGPT
Reads the Productive Help Center. Two call shapes (mutually exclusive): - Search: {query} — returns ranked article titles, URLs, and article content as markdown, with each image marked inline as [image N] instead of its URL; an empty articles array when nothing matches. - Images: {images_for_article_id, image_numbers} — returns each of those placeholders as ready-to-paste image markdown, for an article an earlier search already returned. Only articles from the globally-scoped Help corpus are read — no account-specific data.

search_organization_data

ChatGPT
Keyword search across organization-wide configuration and metadata. Resolves ambiguous organization-specific terms (e.g. "CRM" could be a team, custom field, or pipeline) that cannot be determined from context alone. Searches across: workflows, workflow statuses, roles, subsidiaries, custom fields, custom field options, teams, document types, service types, holiday calendars, holidays, placeholders, events, pipelines, deal statuses, and saved filters. Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).

search_project_data

ChatGPT
Keyword search across project-scoped configuration and structures within a specific project. Finds task lists, folders, custom fields, workflow statuses, and other project-specific data. Resolves ambiguous project-specific terms (e.g. "Backlog" could be a folder, task list, or workflow status). Returns up to 5 matches per type. Empty results may warrant retrying with alternative terms (broader keywords, synonyms).

search_records

ChatGPT
Keyword and semantic search across records by name or text content. Does NOT filter by properties, type, or status — use query/filter tools for property-based lookups. "type" accepts multiple entries for cross-type or ambiguous searches. "keywordSearchQuery" is the primary input; add "semanticSearchQuery" when phrasing may differ from record names (it may not be available on its own). For pages/docs, type "page" returns results with page hierarchy. For people: "person" covers logged-in users (employees, contractors, clients), "contact" covers CRM contacts without login. Include both only when genuinely ambiguous. Empty results often mean a keyword mismatch — try synonyms or broader terms. "deepSearch: true" (with "keywordSearchQuery") searches within record content (descriptions, page bodies), not just names. No effect on "semanticSearchQuery".

update_resource

ChatGPT
Update one or more records of a given resource type. All provided fields are treated as changed — no need for a separate dirtyFields list. Use describe_resource with include: ["fields"] first to learn available fields. Provide a single-item array to update one record, or multiple items for bulk update.

create_resource

Claude

delete_resource

Claude

describe_report

Claude

describe_resource

Claude

get_current_person_and_organization

Claude

load_resource

Claude

load_skills

Claude

perform_action

Claude

productive_domain

Claude

query_report

Claude

query_resources

Claude

read_file_from_url

Claude

search_organization_data

Claude

search_project_data

Claude

search_records

Claude

search_resource

Claude

update_resource

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/productive-io"><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/productive-io)