Convex MCP
Enables building a stateless MCP endpoint on top of Convex, allowing AI agents like Claude to discover and interact with Convex backend functions as tools, prompts, and resources.
README
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 ā Expose Convex functions as MCP tools
- Prompts ā Define MCP prompts with Zod args
- Resources ā 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
| Function | Description |
|---|---|
defineMcpServer(...) |
Create an MCP server with tools, prompts, and resources |
tool(ref, opts) |
Register a Convex function as an MCP tool |
prompt(opts, handler) |
Register an MCP prompt |
resource(ref, opts) |
Register a fixed MCP resource |
resourceTemplate(ref, opts) |
Register a templated MCP resource |
bearerAuth(opts) |
Add Bearer token auth |
License
Contacts
For custom work or enterprise needs, reach out to Alessia & Elia directly: š© founders@vibeflow.ai
- š Website: vibeflow.ai
- š App: app.vibeflow.ai
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.