About tRPC <-> MCP
tRPC <-> MCP serves tRPC routes as an MCP server. Developers enable individual routes through tRPC meta and run the generated server over stdio using trpc-mcp.
Key features
- 01Exposes tRPC routes as MCP tools
- 02Per-route enablement through meta configuration
- 03Zod-based input and output schemas
- 04Stdio transport support
Use cases
- 01Adding MCP access to an existing tRPC API
- 02Letting AI assistants call existing tRPC procedures
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEtRPC <-> MCP
Serve tRPC routes via MCP.
Usage
2. Add to meta
import { initTRPC } from '@trpc/server';
import { type McpMeta } from 'trpc-to-openapi';
const t = initTRPC.meta<McpMeta>().create();
3. Enable for routes
export const appRouter = t.router({
sayHello: t.procedure
.meta({ openapi: { enabled: true, description: 'Greet the user' } })
.input(z.object({ name: z.string() }))
.output(z.object({ greeting: z.string() }))
.query(({ input }) => {
return { greeting: `Hello ${input.name}!` };
});
});
4. Serve
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
import { createMcpServer } from 'trpc-mcp';
const mcpServer = createMcpServer(
{ name: 'trpc-mcp-example', version: '0.0.1' },
appRouter,
);
const transport = new StdioServerTransport();
await mcpServer.connect(transport);
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.