Mcp is a Model Context Protocol (MCP) server: The Teamwork.com official MCP server helps teams efficiently manage client projects with AI. Because it speaks the Model Context Protocol, AI assistants can use Mcp as a set of callable tools instead of you copy-pasting between apps.
You can run Mcp two ways: connect to the hosted endpoint at https://mcp.ai.teamwork.com with no local install, or run it on your own machine via the Docker image docker.io/teamwork/mcp:v1.37.0. Configuration happens through environment variables — you'll need TW_MCP_BEARER_TOKEN. The current release is v1.37.0, published under the MIT license, with source at teamwork/mcp on GitHub, where it has earned 25 stars.
On mcp.site, Mcp sits in the AI & Agents category. Any MCP client can use it — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed among them — via the install snippets below. If you maintain Mcp for teamwork.com, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
