Mcp is a Model Context Protocol (MCP) server: Generate, audit, and maintain legal policies that match what your code actually does. In practice that means any MCP-compatible AI assistant can call Mcp's tools directly — the model decides when to use them in a conversation or agent run.
You can run Mcp two ways: connect to the hosted endpoint at https://policyforge.co/api/mcp with no local install, or run it on your own machine via the npm package @policyforge/mcp. Configuration happens through environment variables — you'll need POLICYFORGE_API_KEY. The current release is v0.6.1, with source at PolicyForge/mcp on GitHub.
Mcp is listed under Development on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Mcp for policyforge.co, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
