Convex MCP

Try Convex MCP instantly in the cloud - works out of the box with VibeFlow.

Build a stateless MCP endpoint on top of Convex.

This package provides a simple wrapper to automatically translate your Convex backend functions into a standard MCP server, allowing any AI agent (like Claude, Cursor, etc.) to discover and interact with them.

Testing inside VibeFlow

You can easily test your Convex MCP server inside VibeFlow:

Install

npm install @vibeflowai/convex-mcp

Features

• Tools – Expose Convex functions as MCP tools
• Prompts – Define MCP prompts with Zod args
• Resources – Serve static and templated MCP resources

Quick Start

Define your MCP server:

// convex/mcp.ts
import { api, internal } from "./_generated/api";
import { defineMcpServer, tool, prompt, resource, promptResult, assistantText, userText } from "@vibeflowai/convex-mcp";

export const mcp = defineMcpServer({
  name: "my-app",
  version: "0.1.0",
  tools: {
    users: {
      get: tool(api.users.get, {
        kind: "query",
        description: "Fetch a user by id",
        args: (z) => ({ userId: z.string() }),
      }),
    },
  },
  prompts: {
    onboarding: prompt(
      { args: (z) => ({ name: z.string() }) },
      async ({ name }) => promptResult([assistantText(`Welcome ${name}!`)])
    ),
  },
  resources: {
    config: resource(api.resources.config, {
      kind: "query",
      uri: "config://app",
      mimeType: "application/json",
    }),
  },
});

Mount it:

// convex/http.ts
import { httpRouter } from "convex/server";
import { mcp } from "./mcp";

const http = httpRouter();
mcp.addHttpRoutes(http);

export default http;

Auth

import { bearerAuth } from "@vibeflowai/convex-mcp";

mcp.addHttpRoutes(http, {
  auth: bearerAuth({ env: "MCP_AUTH_TOKEN" }),
});

API Reference

License

MIT

Contacts

For custom work or enterprise needs, reach out to Alessia & Elia directly:
📩 [email protected]

• 🌐 Website: vibeflow.ai
• 🚀 App: app.vibeflow.ai