DidWork is a Model Context Protocol (MCP) server: Verify that an agent's claimed outcome actually happened, using independently gathered evidence. In practice that means any MCP-compatible AI assistant can call DidWork's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the npm package @didwork/mcp speaks MCP over stdio on your machine. The current release is v0.0.7.
DidWork is listed under AI & Agents 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 DidWork for didwork.sh, claim this listing to verify ownership, earn the Verified badge, and keep the details current.