Two interfaces published as MCP tools, and an agent that discovers and calls them over the wire — the server half and the client half of MCP in one config. Marking an interface with mcp.enabled turns it into a tool whose input schema comes from its own assertions; the agent lists and calls those tools at run time rather than restating them. Runs on a self-hosted engine with no database and no credential beyond a model key.
Turn your Postgres data into secure MCP tools any AI client (Claude Desktop, Claude Code, Cursor) can call. Two-tier auth: one shared token for yourself, or per-user tenant-scoped tokens for your customers - minted via an HS256 exchange or verified directly against your OIDC provider's JWKS (Auth0, Clerk, Cognito). Every tool reuses the same in-config token checks as a normal Air Pipe route. Tool discovery (tools/list) is gated behind the same per-user token via list_authorizer, so unauthenticated clients cannot enumerate your tools or their input schemas (engine >= 1.7.0).
The smallest useful MCP server: two tools over one Postgres table, guarded by a single shared token, in one config file. Point Claude Desktop, Claude Code, Cursor or any MCP client at your database with no SDK, no Node project and nothing to host. An Air Pipe interface is an HTTP route; add an mcp block and the same interface is also an MCP tool, secured by the same in-config token check. Tool discovery (tools/list) is gated by that same token via list_authorizer, so an unauthenticated client cannot even enumerate your tools or their input schemas. Includes a seed endpoint that creates the table and sample data in one curl.