Teamwork-MCP
Verified Safeby Vizioz
Overview
An MCP server for AI agents to interact with the Teamwork.com API, enabling management of projects, tasks, people, companies, and reporting within Teamwork.
Installation
npx @vizioz/teamwork-mcp --domain=your-company --user=your-email@example.com --pass=your-passwordEnvironment Variables
- TEAMWORK_DOMAIN
- TEAMWORK_USERNAME
- TEAMWORK_PASSWORD
- TEAMWORK_PROJECT_ID
- SOLUTION_ROOT_PATH
- ALLOW_TOOLS
- DENY_TOOLS
- DISABLE_LOGGING
- LOG_LEVEL
Security Notes
Credentials (`TEAMWORK_USERNAME`, `TEAMWORK_PASSWORD`) are handled via environment variables, .env file, or command-line arguments, which is standard. All API communication is expected to be over HTTPS as enforced by the API client. Authentication uses Basic Auth which, while functional, is generally less secure than token-based approaches if not exclusively used over HTTPS. Logging of sensitive information in request/response bodies could be a concern if the log files are not adequately secured. The server uses file-based logging only, never printing sensitive data to the console, and redacts Authorization headers in logs, which is a good practice.
Similar Servers
backlog-mcp-server
Integrate Backlog API with AI agents (e.g., Claude) to manage projects, issues, wikis, and Git repositories through natural language commands.
plane-mcp-server
Enables AI agents and developer tools to programmatically interact with a Plane project management workspace by providing a set of tools.
vikunja-mcp
An MCP server enabling AI assistants to programmatically manage tasks, projects, and other entities within a Vikunja task management instance.
trello-mcp-server
Provides an AI-agent-friendly interface (MCP server) to interact with the Trello API for managing boards, lists, cards, and other Trello resources.