com.teamwork/mcp MCP Server
com.teamwork/mcp
AI-powered project management for Teamwork.com—read and write projects, tasks, and team data via Claude or Cursor.
What is the com.teamwork/mcp MCP server?
The Teamwork MCP server is an official Model Context Protocol integration that connects Large Language Models to Teamwork.com, enabling AI agents to manage projects, tasks, and team collaboration. It provides standardized access to Teamwork.com's Projects, Desk, Spaces, and Chat modules through create, read, and update operations.
This server lets AI assistants like Claude interact directly with your Teamwork.com workspace. You can query projects and tasks, create work items, update statuses, and manage team data—all through natural language. It's production-ready with multiple deployment options (HTTP, STDIO, Docker) and supports both bearer token and OAuth2 authentication.
How to install com.teamwork/mcp
Copy-paste configuration for popular MCP clients.
TW_MCP_BEARER_TOKENrequiredsecretAPI key generated from the Teamwork.com OAuth2 process: https://apidocs.teamwork.com/guides/teamwork/app-login-flow
TW_MCP_LOG_FORMATChoose log output format between 'text' or 'json'. Default is 'text'.
TW_MCP_LOG_LEVELChoose log level between 'debug', 'info', 'warn' or 'error'. Default is 'info'.
AuthorizationrequiredsecretAPI key generated from the Teamwork.com OAuth2 process: https://apidocs.teamwork.com/guides/teamwork/app-login-flow
Tools & capabilities
Tools this server exposes to the agent.
Projects tools— Create, read, and update operations for Teamwork.com projects, tasks, tags, and timersDesk tools— Manage Teamwork Desk tickets, customers, and support workflowsSpaces tools— Work with Teamwork Spaces, pages, and collaborative documentsChat tools— Access Teamwork Chat conversations and messages
Use cases
- Query project status and task lists to summarize team progress in natural language
- Create and assign tasks to team members based on conversation or email content
- Update task statuses, add comments, and manage project timelines via AI instructions
- Search and retrieve customer tickets from Teamwork Desk for support automation
- Generate reports on project metrics, team workload, and task completion rates
com.teamwork/mcp MCP server FAQ
It's an official Model Context Protocol server that connects AI assistants (Claude, Cursor) to Teamwork.com, allowing them to read and write projects, tasks, tickets, spaces, and chat data.
The MCP server itself is open-source. You need a valid Teamwork.com account and API credentials (bearer token or OAuth2) to use it.
See the Usage Guide in the repository. You'll need to enable MCP in your Teamwork.com settings, generate an API token, and configure your client (Cursor/Claude) with the server's HTTP or STDIO endpoint.
Bearer token authentication and OAuth2 integration with Teamwork.com are both supported.
Yes, the server supports an optional read-only mode for safety, preventing create/update/delete operations.
HTTP server (cloud/multi-client), STDIO server (desktop/development), Docker container, and an HTTP CLI tool for testing.
README (reference)
Source of truth, from the repository.
Teamwork MCP Server
Model Context Protocol server for Teamwork.com integration with Large Language Models
📌 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.
📖 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.
🤖 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.
✨ 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.
🚀 Available Servers
This project provides three different ways to interact with the Teamwork.com MCP server:
📡 HTTP Server
Production-ready HTTP server for cloud deployments and multi-client support.
📖 Full HTTP Server Documentation
Quick start:
TW_MCP_SERVER_ADDRESS=:8080 go run cmd/mcp-http/main.go
💬 STDIO Server
Direct STDIO interface for desktop applications and development environments.
📖 Full STDIO Server Documentation
Quick start:
TW_MCP_BEARER_TOKEN=your-token go run cmd/mcp-stdio/main.go
🛠️ HTTP CLI
Command-line tool for testing and debugging MCP server functionality.
Quick start:
go run cmd/mcp-http-cli/main.go -mcp-url=https://mcp.example.com list-tools
📋 Prerequisites
- Go 1.27 or later
- Valid Teamwork.com API credentials (bearer token or OAuth2 setup)
🧪 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.
🏗️ Architecture
├── cmd/
│ ├── mcp-http/ # HTTP server implementation
│ ├── mcp-stdio/ # STDIO server implementation
│ ├── mcp-http-cli/ # CLI tool for testing via HTTP
│ ├── mcp-test/ # Walks tool handlers against a real site
│ ├── mcp-tokens/ # Token-cost report for the tool surface
│ └── docs-gen/ # Generates the tool reference (Markdown + GitHub Pages)
├── pkg/ # Importable by other MCP servers built on this one
│ ├── auth/ # Authentication helpers (bearer & OAuth2 token handling)
│ ├── cli/ # -toolsets flag parsing
│ ├── config/ # Configuration management (env, flags), MCP server setup
│ ├── helpers/ # Shared utility functions (errors, link helpers, tool parsing)
│ ├── request/ # HTTP request primitives / Teamwork API wiring
│ ├── testutil/ # Product-neutral test mocks
│ ├── toolsets/ # Tool framework and registration logic
│ └── twctx/ # Per-request values derived from the bearer token
├── internal/ # This server's own tools, not importable elsewhere
│ ├── twprojects/ # Teamwork project/domain tools (tasks, tags, timers, etc.)
│ ├── twdesk/ # Teamwork Desk tools (tickets, customers, etc.)
│ ├── twspaces/ # Teamwork Spaces tools (spaces, pages, etc.)
│ └── twchat/ # Teamwork Chat tools (conversations, messages)
├── examples/ # Usage & integration examples (LangChain Node/Python)
├── docs/usage/ # End-user setup & connection guide
├── Makefile # Common developer tasks
├── Dockerfile # Container build configuration
├── CODE_OF_CONDUCT.md # Community guidelines
├── CONTRIBUTING.md # Contribution guide
└── SECURITY.md # Security policy
Related MCP servers
Topics, semantic search, tasks, projects, areas and documents in TY Agent Drive.

Agent-first tech news: ranked story clusters, coverage and discussion links, trends, and events.
View repository →Mercado Libre keyword & competitor intelligence for AI agents across all 18 ML markets.
View repository →Adolescent psychiatry library focused on the medication decisions parents wrestle with.
Read-only access to your own TTMT trading data: trades, signals, channels, performance and risk.
Read and write your Teleprompter.com scripts and folders: list, create, update, and organize.
