Lets AI agents manage Teamwork.com projects, tickets, spaces, and chat through the Model Context Protocol.
Also known as teamwork/mcp, mcp
- Stars
- 28
- Tools
- โ
- Downloads, 30 days
- โ
- Latest version
- 1.62.2
- Last commit
- Nov 15, 2026
- License
- MIT
What is Teamwork.com MCP?
Teamwork.com lets AI agents manage Teamwork.com projects, tickets, spaces, and chat through the Model Context Protocol.
Summary generated from the project's README
About Teamwork.com MCP server
Managing Teamwork.com projects, tickets, and communications through AI agents is possible with this integration. It provides a standardized way for large language models to interact with your existing workflows by exposing tools for Projects, Desk, Spaces, and Chat. Developers can use this to automate tasks like managing tasks, tags, timers, or customer tickets directly from an AI client.
Users can deploy the server using either an HTTP interface for cloud environments or a STDIO interface for local desktop applications. Authentication is handled via bearer tokens or OAuth2, and the system supports an optional read-only mode to ensure safety during operations. The server is built with Go and requires version 1.27 or later to run.
This toolset is designed for different deployment needs, offering a production-ready HTTP server for multi-client support and a command-line tool for testing and debugging. It covers a wide range of internal domains including twprojects, twdesk, twspaces, and twchat to ensure comprehensive coverage of the Teamwork.com platform.
What you can do with it
- 1Automate project management tasksAn AI agent can manage various project operations including tasks, tags, and timers.
- 2Handle customer support ticketsDevelopers can use the Desk tools to manage customer interactions and tickets.
- 3Securely test server functionalityDevelopers can use the included CLI tool to debug and test the MCP server via HTTP.
Written from the project's README. Every use case is checked against a quote from it.
How to install Teamwork.com MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Teamwork.com MCP in Claude Code
$ claude mcp add --env 'TW_MCP_BEARER_TOKEN=<YOUR_TW_MCP_BEARER_TOKEN>' mcp -- docker run -i --rm docker.io/teamwork/mcp:v1.62.2Install Teamwork.com MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/teamwork/mcp:v1.62.2"
],
"env": {
"TW_MCP_BEARER_TOKEN": "<YOUR_TW_MCP_BEARER_TOKEN>"
}
}
}
}Install Teamwork.com MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/teamwork/mcp:v1.62.2"
],
"env": {
"TW_MCP_BEARER_TOKEN": "<YOUR_TW_MCP_BEARER_TOKEN>"
}
}
}
}Install Teamwork.com MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp","type":"stdio","command":"docker","args":["run","-i","--rm","docker.io/teamwork/mcp:v1.62.2"],"env":{"TW_MCP_BEARER_TOKEN":"<YOUR_TW_MCP_BEARER_TOKEN>"}}'Install Teamwork.com MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/teamwork/mcp:v1.62.2"
],
"env": {
"TW_MCP_BEARER_TOKEN": "<YOUR_TW_MCP_BEARER_TOKEN>"
}
}
}
}Install Teamwork.com MCP in Codex
$ codex mcp add mcp --env 'TW_MCP_BEARER_TOKEN=<YOUR_TW_MCP_BEARER_TOKEN>' -- docker run -i --rm docker.io/teamwork/mcp:v1.62.2Install Teamwork.com MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp] command = "docker" args = ["run", "-i", "--rm", "docker.io/teamwork/mcp:v1.62.2"] [mcp_servers.mcp.env] TW_MCP_BEARER_TOKEN = "<YOUR_TW_MCP_BEARER_TOKEN>"
Install Teamwork.com MCP in Gemini CLI
$ gemini mcp add -s user -e 'TW_MCP_BEARER_TOKEN=<YOUR_TW_MCP_BEARER_TOKEN>' mcp docker -- run -i --rm docker.io/teamwork/mcp:v1.62.2Install Teamwork.com MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/teamwork/mcp:v1.62.2"
],
"env": {
"TW_MCP_BEARER_TOKEN": "<YOUR_TW_MCP_BEARER_TOKEN>"
}
}
}
}Configuration
TW_MCP_BEARER_TOKENRequiredSecretAPI key generated from the Teamwork.com OAuth2 process: https://apidocs.teamwork.com/guides/teamwork/app-login-flow
NODE_EXTRA_CA_CERTSTW_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'.
TW_MCP_SERVER_ADDRESS
| Name | Description | |
|---|---|---|
| TW_MCP_BEARER_TOKEN | API key generated from the Teamwork.com OAuth2 process: https://apidocs.teamwork.com/guides/teamwork/app-login-flow | RequiredSecret |
| NODE_EXTRA_CA_CERTS | โ | |
| TW_MCP_LOG_FORMAT | Choose log output format between 'text' or 'json'. Default is 'text'. | |
| TW_MCP_LOG_LEVEL | Choose log level between 'debug', 'info', 'warn' or 'error'. Default is 'info'. | |
| TW_MCP_SERVER_ADDRESS | โ |
Automated checks
Ran Nov 12, 2026Full report โPassed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packageNot checked
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesNot checked
README
View on GitHubTeamwork MCP Server
Model Context Protocol server for Teamwork.com integration with Large Language Models
๐ 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.
๐ 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.
๐ค 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.
โจ 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.
๐ Available Servers
This project provides three different ways to interact with the Teamwork.com MCP server:
๐ก HTTP Server
Production-ready HTTP server for cloud deployments and multi-client support.
๐ Full HTTP Server Documentation
Quick start:
TW_MCP_SERVER_ADDRESS=:8080 go run cmd/mcp-http/main.go
๐ฌ STDIO Server
Direct STDIO interface for desktop applications and development environments.
๐ Full STDIO Server Documentation
Quick start:
TW_MCP_BEARER_TOKEN=your-token go run cmd/mcp-stdio/main.go
๐ ๏ธ HTTP CLI
Command-line tool for testing and debugging MCP server functionality.
๐ Full HTTP CLI Documentation
Quick start:
go run cmd/mcp-http-cli/main.go -mcp-url=https://mcp.example.com list-tools
๐ Prerequisites
- Go 1.27 or later
- Valid Teamwork.com API credentials (bearer token or OAuth2 setup)
๐งช 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.
๐๏ธ Architecture
โโโ cmd/
โ โโโ mcp-http/ # HTTP server implementation
โ โโโ mcp-stdio/ # STDIO server implementation
โ โโโ mcp-http-cli/ # CLI tool for testing via HTTP
โ โโโ mcp-test/ # Walks tool handlers against a real site
โ โโโ mcp-tokens/ # Token-cost report for the tool surface
โ โโโ docs-gen/ # Generates the tool reference (Markdown + GitHub Pages)
โโโ pkg/ # Importable by other MCP servers built on this one
โ โโโ auth/ # Authentication helpers (bearer & OAuth2 token handling)
โ โโโ cli/ # -toolsets flag parsing
โ โโโ config/ # Configuration management (env, flags), MCP server setup
โ โโโ helpers/ # Shared utility functions (errors, link helpers, tool parsing)
โ โโโ request/ # HTTP request primitives / Teamwork API wiring
โ โโโ testutil/ # Product-neutral test mocks
โ โโโ toolsets/ # Tool framework and registration logic
โ โโโ twctx/ # Per-request values derived from the bearer token
โโโ internal/ # This server's own tools, not importable elsewhere
โ โโโ twprojects/ # Teamwork project/domain tools (tasks, tags, timers, etc.)
โ โโโ twdesk/ # Teamwork Desk tools (tickets, customers, etc.)
โ โโโ twspaces/ # Teamwork Spaces tools (spaces, pages, etc.)
โ โโโ twchat/ # Teamwork Chat tools (conversations, messages)
โโโ examples/ # Usage & integration examples (LangChain Node/Python)
โโโ docs/usage/ # End-user setup & connection guide
โโโ Makefile # Common developer tasks
โโโ Dockerfile # Container build configuration
โโโ CODE_OF_CONDUCT.md # Community guidelines
โโโ CONTRIBUTING.md # Contribution guide
โโโ SECURITY.md # Security policy
Teamwork.com MCP questions
How do I add Teamwork.com MCP to Claude Code?
Run claude mcp add --env 'TW_MCP_BEARER_TOKEN=<YOUR_TW_MCP_BEARER_TOKEN>' mcp -- docker run -i --rm docker.io/teamwork/mcp:v1.62.2 in your terminal. Add --scope user to make it available in every project.
How do I add Teamwork.com MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can the Teamwork.com MCP server do?
It exposes Teamwork.com create/read/update operations across Projects, Desk, Spaces, and Chat so AI agents can run project management tasks.
How do I authenticate the Teamwork.com MCP server?
It supports a bearer token or OAuth2 integration with Teamwork.com.
Which transport modes does the Teamwork.com MCP server support?
It offers HTTP and STDIO interfaces for different deployment scenarios, plus an HTTP CLI for testing.
Can I restrict the Teamwork.com MCP server to read-only operations?
Yes, an optional read-only mode limits the server to read-only operations for safety.
What are the prerequisites for running the Teamwork.com MCP server?
You need Go 1.27 or later and valid Teamwork.com API credentials, either a bearer token or OAuth2 setup.