Teamwork MCP Server
MCP serverDev toolsThis connects your AI to Teamwork.com so it can help your team manage client projects. Once it is added, everyday project work can be handled through your AI, making it easier to keep client work on track.
Available today. Use it from your connected AI after setup.
Needs your own TW MCP Bearer account. Credentials stay encrypted.
After adding it, try asking your AI about your client projects in Teamwork and let it help you keep them organized.
Then ask your AI: use Teamwork MCP Server
What your AI can do with it
- Manage client projects in Teamwork.com through your AI
- Ask about your client projects and work on them in the same conversation
- Keep client project work moving without leaving your chat with your AI
- Give your whole team an AI helper for client project management
From the project's README
As published by teamwork/mcp in README.md.
Model Context Protocol server for Teamwork.com integration with Large Language Models
π Are you a Teamwork.com user wanting to connect AI tools to your Teamwork.com site right now? Jump straight to the Usage Guide for tokens, enabling MCP, and client configuration examples.
π Overview
This MCP (Model Context Protocol) server enables seamless integration between Large Language Models and Teamwork.com. It provides a standardized interface for LLMs to interact with Teamwork.com projects, allowing AI agents to perform various project management operations.
π€ What is MCP?
Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to LLMs. This server describes all the actions available in Teamwork.com (tools) in a way that LLMs can understand and execute through AI agents.
β¨ Features
- Multiple Transport Modes: HTTP and STDIO interfaces for different deployment scenarios
- Secure Authentication: Bearer token and OAuth2 integration with Teamwork.com
- Tool Framework: Extensible toolset architecture for adding new capabilities
- Production Ready: Comprehensive logging, monitoring, and observability
- Read-Only Mode: Optional restriction to read-only operations for safety
See the auto-generated Tool Reference for every create/read/update operation exposed across Projects, Desk, Spaces, and Chat, or browse the same catalogue with per-tool descriptions and a search filter at teamwork.github.io/mcp.
π Available Servers
This project provides three different ways to interact with the Teamwork.com MCP server:
π‘ HTTP Server
Production-ready HTTP server for cloud deployments and multi-client support.
π Full HTTP Server Documentation
Quick start:
TW_MCP_SERVER_ADDRESS=:8080 go run cmd/mcp-http/main.go
π¬ STDIO Server
Direct STDIO interface for desktop applications and development environments.
π Full STDIO Server Documentation
Quick start:
TW_MCP_BEARER_TOKEN=your-token go run cmd/mcp-stdio/main.go
π οΈ HTTP CLI
Command-line tool for testing and debugging MCP server functionality.
π Full HTTP CLI Documentation
Quick start:
go run cmd/mcp-http-cli/main.go -mcp-url=https://mcp.example.com list-tools
π Prerequisites
- Go 1.27 or later
- Valid Teamwork.com API credentials (bearer token or OAuth2 setup)
π§ͺ Development & Testing
Running Tests
# Run all tests
go test ./...
# Run specific package tests
go test ./internal/twprojects/
MCP Inspector
For debugging purposes, use the MCP Inspector tool:
NODE_EXTRA_CA_CERTS=letsencrypt-stg-root-x1.pem npx @modelcontextprotocol/inspector node build/index.js
[!IMPORTANT] Note: The
NODE_EXTRA_CA_CERTSenvironment variable is required when using OAuth2 authentication with the Let's Encrypt certification authority. Download the certificate here.
ποΈ Architecture
βββ cmd/
β βββ mcp-http/ # HTTP server implementation
β βββ mcp-stdio/ # STDIO server implementation
β βββ mcp-http-cli/ # CLI tool for testing via HTTP
β βββ mcp-test/ # Walks tool handlers against a real site
β βββ mcp-tokens/ # Token-cost report for the tool surface
β βββ docs-gen/ # Generates the tool reference (Markdown + GitHub Pages)
βββ pkg/ # Importable by other MCP servers built on this one
β βββ auth/ # Authentication helpers (bearer & OAuth2 token handling)
β βββ cli/ # -toolsets flag parsing
β βββ config/ # Configuration management (env, flags), MCP server setup
β βββ helpers/ # Shared utility functions (errors, link helpers, tool parsing)
β βββ request/ # HTTP request primitives / Teamwork API wiring
β βββ testutil/ # Product-neutral test mocks
β βββ toolsets/ # Tool framework and registration logic
β βββ twctx/ # Per-request values derived from the bearer token
βββ internal/ # This server's own tools, not importable elsewhere
β βββ twprojects/ # Teamwork project/domain tools (tasks, tags, timers, etc.)
β βββ twdesk/ # Teamwork Desk tools (tickets, customers, etc.)
β βββ twspaces/ # Teamwork Spaces tools (spaces, pages, etc.)
β βββ twchat/ # Teamwork Chat tools (conversations, messages)
βββ examples/ # Usage & integration examples (LangChain Node/Python)
βββ docs/usage/ # End-user setup & connection guide
βββ Makefile # Common developer tasks
βββ Dockerfile # Container build configuration
βββ CODE_OF_CONDUCT.md # Community guidelines
βββ CONTRIBUTING.md # Contribution guide
βββ SECURITY.md # Security policy
Signals
- GitHub stars
- 25
- Forks
- 17
- Last commit
- Sep 2026
Advanced
- Delivery
- mcp MCP server β your ahel gateway (mcp.ahel.ai) β every connected AI client.
- Catalog kind
- mcp-server
- Gateway key
com-teamwork-mcp- Source
- github.com/teamwork/mcp
- Hosted endpoint
https://mcp.ai.teamwork.com/sse