Productive.io MCP Server
Enables AI assistants to interact with a Productive.io workspace for managing projects, tasks, time entries, budgets, and invoices through natural language.
README
Productive.io MCP Server
An MCP (Model Context Protocol) server for Productive.io that enables AI assistants like Claude to interact with your Productive.io workspace — managing projects, tasks, time entries, budgets, and more.
Supports two transport modes:
- stdio (default) — Claude launches it as a local subprocess
- HTTP (with
--httpflag) — runs as an Express web server for remote/team use
Prerequisites
- Node.js 18+
- A Productive.io account with API access
- API Token — generate one in Productive.io under Settings → API integrations
- Organization ID — found in your Productive.io account settings
Installation
git clone <your-repo-url> productive-mcp-server
cd productive-mcp-server
npm install
cp .env.example .env
# Edit .env with your credentials
npm run build
Configuration
| Variable | Required | Description |
|---|---|---|
PRODUCTIVE_API_TOKEN |
Yes | Your Productive.io API token |
PRODUCTIVE_ORG_ID |
Yes | Your Productive.io organization ID |
PORT |
No | HTTP server port (default: 3000) |
Running
stdio mode (default — for local use)
# Development
npm run dev
# Production (after build)
npm start
HTTP mode (for remote/team use)
# Development
npm run dev:http
# Production (after build)
npm run start:http
The HTTP server exposes:
POST /mcp— MCP protocol endpointGET /health— health check
Connecting to Claude Desktop
Add this to your Claude Desktop configuration (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"productive": {
"command": "node",
"args": ["/absolute/path/to/productive-mcp-server/dist/index.js"],
"env": {
"PRODUCTIVE_API_TOKEN": "your_api_token_here",
"PRODUCTIVE_ORG_ID": "your_org_id_here"
}
}
}
}
Connecting to Claude Code
stdio mode
claude mcp add productive -- node /absolute/path/to/productive-mcp-server/dist/index.js
Set the environment variables before running Claude Code, or add them to your shell profile:
export PRODUCTIVE_API_TOKEN=your_api_token_here
export PRODUCTIVE_ORG_ID=your_org_id_here
HTTP mode
Start the server first:
cd /path/to/productive-mcp-server
PRODUCTIVE_API_TOKEN=your_token PRODUCTIVE_ORG_ID=your_org npm run start:http
Then connect Claude Code:
claude mcp add productive --transport http http://localhost:3000/mcp
Connecting to VS Code
Add to your VS Code user settings JSON (.vscode/settings.json or user settings):
stdio mode
{
"mcp": {
"servers": {
"productive": {
"command": "node",
"args": ["/absolute/path/to/productive-mcp-server/dist/index.js"],
"env": {
"PRODUCTIVE_API_TOKEN": "your_api_token_here",
"PRODUCTIVE_ORG_ID": "your_org_id_here"
}
}
}
}
}
HTTP mode
{
"mcp": {
"servers": {
"productive": {
"type": "http",
"url": "http://localhost:3000/mcp"
}
}
}
}
Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
productive_list_projects |
List/search projects | company_id, project_type_id, status, query |
productive_get_project |
Get project by ID | id, include |
productive_create_project |
Create a project | name, project_type_id, company_id |
productive_update_project |
Update a project | id, name, project_type_id |
productive_list_tasks |
List/filter tasks | project_id, assignee_id, status, query |
productive_get_task |
Get task by ID | id, include |
productive_create_task |
Create a task | title, task_list_id, assignee_id |
productive_update_task |
Update a task | id, title, closed, assignee_id |
productive_list_time_entries |
List time entries | person_id, project_id, after, before |
productive_log_time |
Log a time entry | person_id, service_id, date, time |
productive_list_people |
List team members | status, company_id, query |
productive_get_person |
Get person by ID | id, include |
productive_list_deals |
List budgets/deals | project_id, company_id, deal_status |
productive_get_deal |
Get deal by ID | id, include |
productive_list_companies |
List companies | status, query |
productive_get_company |
Get company by ID | id, include |
productive_list_bookings |
List bookings | person_id, project_id, after, before |
productive_list_services |
List services | deal_id |
Invoicing Tools (Draft Only)
All invoice tools create and manage draft invoices only. Finalization (assigning an invoice number) must always be done manually in the Productive.io UI.
| Tool | Description | Key Parameters |
|---|---|---|
productive_list_invoices |
List/filter invoices | company_id, deal_id, invoice_status, date range |
productive_get_invoice |
Get full invoice details with line items | id |
productive_create_invoice |
Create a new empty draft invoice | company_id, document_type_id, subsidiary_id |
productive_update_invoice |
Update a draft invoice | id, subject, note, dates |
productive_create_invoice_from_previous |
Clone an invoice (line items + budget links) | source_invoice_id, optional overrides |
productive_create_invoice_like_last_for_client |
Clone a client's most recent invoice | company_id, how_many_back |
productive_list_line_items |
List line items for an invoice | invoice_id |
productive_create_line_item |
Add a line item to a draft invoice | invoice_id, description, quantity, unit_price, unit_id |
productive_update_line_item |
Update an existing line item | id, description, quantity, unit_price |
productive_delete_line_item |
Delete a line item | id |
productive_list_invoice_attributions |
List budget links for an invoice | invoice_id |
productive_create_invoice_attribution |
Link a draft invoice to a budget | invoice_id, deal_id, amount |
productive_list_document_types |
List available document types | subsidiary_id, status |
productive_list_subsidiaries |
List your company subsidiaries | status |
productive_list_tax_rates |
List available tax rates | status |
All list tools support page, page_size, and sort parameters.
Testing with MCP Inspector
npx @modelcontextprotocol/inspector node dist/index.js
This opens an interactive UI to test each tool.
Rate Limits
Productive.io enforces:
- 100 requests per 10 seconds
- 4,000 requests per 30 minutes
The server implements automatic retry with exponential backoff for 429 responses (up to 3 retries).
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.