mcp-on-vercel

@xarical

About mcp-on-vercel

MCP Server on Vercel template

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-on-vercel": {
      "command": "node",
      "args": [
        "scripts/test-sse-client.mjs",
        "YOUR_MCP_SERVER_URL"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-on-vercel?

A template Model Context Protocol (MCP) server built with the TypeScript SDK, designed for deployment on Vercel. It lets developers define custom tools, prompts, and resources and test them locally or on Vercel’s infrastructure.

How to use mcp-on-vercel?

Install dependencies with npm install, then run the dev server with vercel dev. Edit api/server.ts to add your tools, prompts, and resources. Test using the provided SSE or streamable HTTP client scripts.

Key features of mcp-on-vercel

Ready‑to‑deploy MCP server template for Vercel
Supports Server‑Sent Events (SSE) and streamable HTTP transports
Includes test client scripts for both transports
Uses standard TypeScript SDK for tool/resource definitions
Environment variables accessible via process.env

Use cases of mcp-on-vercel

Deploying an MCP server with minimal setup on Vercel
Prototyping and testing MCP tools, prompts, and resources locally
Building a lightweight, serverless MCP endpoint with Redis/Upstash

FAQ from mcp-on-vercel

What runtime or dependencies does it require?

Node.js, the Vercel CLI, and a Redis or Upstash database connected to the Vercel project. Fluid Compute is recommended.

How do I run the server locally?

Run npm install, then vercel dev to start the development server.

How do I deploy the server?

Use the “Deploy to Vercel” button in the README, or manually import the repository and follow Vercel’s prompts.

What transports are supported?

SSE and streamable HTTP. Test scripts are provided in the scripts/ directory.

Where can I define my MCP tools, prompts, and resources?

In the api/server.ts file, following the MCP TypeScript SDK documentation.

Frequently asked questions

What runtime or dependencies does it require?

Node.js, the Vercel CLI, and a Redis or Upstash database connected to the Vercel project. Fluid Compute is recommended.

How do I run the server locally?

Run `npm install`, then `vercel dev` to start the development server.

How do I deploy the server?

Use the “Deploy to Vercel” button in the README, or manually import the repository and follow Vercel’s prompts.

What transports are supported?

SSE and streamable HTTP. Test scripts are provided in the `scripts/` directory.

Where can I define my MCP tools, prompts, and resources?

In the `api/server.ts` file, following the MCP TypeScript SDK documentation.

Comments

Basic information

More Cloud & Infrastructure MCP servers

K8s MCP Server

alexei-led

K8s-mcp-server is a Model Context Protocol (MCP) server that enables AI assistants like Claude to securely execute Kubernetes commands. It provides a bridge between language models and essential Kubernetes CLI tools including kubectl, helm, istioctl, and argocd, allowing AI syste

212

AWS MCP

RafalWilinski

Talk with your AWS using Claude. Model Context Protocol (MCP) server for AWS. Better Amazon Q alternative.

295

🐳 docker-mcp

QuantGeekDev

A docker MCP Server (modelcontextprotocol)

490

Sample Serverless MCP Servers

aws-samples

Sample implementations of AI Agents and MCP Servers running on AWS Serverless compute

239

Nippy

Nippy is drag-and-drop hosting (nippy.host) with an MCP server: connect it and your assistant can publish HTML, folders of photos, or file downloads to a live *.nippy.site URL — and keep editing the site in place at the