Flisk MCP Resources: Give Your Agents Tools That Run Next to Your Services
Agents are only as useful as the tools they can call. An mcp resource in Flisk is a Model Context Protocol server that runs in the same local stack as your services. Docker builds it, flisk up starts it, Traefik routes to it, and its health route gates startup order. What you get flisk resource docs-mcp --type mcp --stack shop flisk up shop The scaffold writes a service.json with appType: "mcp" ,…
Flisk MCP Resources provide agents with tools that operate alongside services in a single local stack. This MCP (Model Context Protocol) server is Docker-built, launched by flisk up, and routed to via Traefik. Its health check is accessible at /health. The server skeleton, created through the flisk scaffold command, generates a service.json with an appType of "mcp," a random port between 4000 and 5999, and /health as the health check path.
The server source, built on the MCP TypeScript SDK with Streamable HTTP transport, includes a placeholder tool named "echo." The three API routes are POST /mcp for client requests, GET /mcp to return a 405 status with Allow: POST, and GET /health to provide a JSON status. Traefik routes the server with its name prefix removed. To check the server's status, make a raw JSON-RPC call using curl.
The scaffold does not support authentication; thus, it is intended for local development behind an *.localhost domain. Tools are added in buildServer() using the SDK's registerTool function, with arguments validated through zod schemas to prevent crashes if invalid arguments are used. The scaffold does not protect against unauthorized access or destructive tools, so developers must implement security measures and limit tool capabilities to protect production data.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.