mcp
Verified Safeby Teamwork
Overview
Enables Large Language Models (LLMs) and AI agents to interact with and manage Teamwork.com projects and Teamwork Desk resources via the Model Context Protocol.
Installation
TW_MCP_SERVER_ADDRESS=:8080 go run cmd/mcp-http/main.goEnvironment Variables
- TW_MCP_BEARER_TOKEN
- TW_MCP_API_URL
- TW_MCP_SERVER_ADDRESS
- TW_MCP_LOG_LEVEL
- OPENAI_API_KEY
- ANTHROPIC_API_KEY
- GOOGLE_API_KEY
Security Notes
The project demonstrates strong security practices, including a dedicated `SECURITY.md` outlining vulnerability reporting and best practices. It uses standard authentication mechanisms (Bearer tokens, OAuth2), explicitly warns against hardcoding API keys, and redacts authorization headers in logs. The server implements middleware for authentication, request tracing (Datadog APM), and error reporting (Sentry). Input parsing for tool arguments is type-safe, reducing injection risks. A whitelist of MCP methods can bypass authentication for necessary initialization/discovery. The STDIO server can be run in a `-read-only` mode for enhanced safety.
Similar Servers
mcpo
Exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers for integration with LLM agents and other applications.
backlog-mcp-server
Integrate Backlog API with AI agents (e.g., Claude) to manage projects, issues, wikis, and Git repositories through natural language commands.
action_mcp
Provides Model Context Protocol (MCP) server capabilities to Ruby on Rails applications, enabling AI assistants to interact with external data sources and tools via JSON-RPC over HTTP/SSE.
mcp-github-project-manager
AI-powered GitHub Project Management, including automated roadmap generation, sprint planning, issue triaging, task breakdown, and comprehensive project workflow automation.