Vercel MCP Server Template

Vercel MCP Server Template

A starter template for deploying Model Context Protocol (MCP) servers on Vercel using TypeScript and Vercel Functions. It includes example tools for rolling dice and checking weather to demonstrate tool integration patterns.

Category
Visit Server

README

Run an MCP Server on Vercel

Usage

Update api/server.js with your tools, prompts, and resources following the MCP TypeScript SDK documentation.

There is also a Next.js version of this template

MCP Client Integration

When adding this server to an MCP client application, use your deployment URL followed by /mcp (Streamable HTTP). The SSE transport is available at /sse:

https://your-deployment-url.vercel.app/mcp

MCP Apps UI hook

This template registers an MCP Apps UI resource at ui://hello_app_panel and links it to the hello_world tool via _meta.ui.resourceUri. MCP hosts that support MCP Apps will render the panel inline and forward tool calls initiated from the UI.

Example Tools

The template includes one example tool to get you started:

  • hello_world - Returns a hello message with an allowlisted style input.

Notes for running on Vercel

  • Make sure you have Fluid compute enabled for efficient execution
  • After enabling Fluid compute, open vercel.json and adjust max duration to 800 if you using a Vercel Pro or Enterprise account
  • Deploy the MCP template

Local dev

  • Run vercel dev for local development
  • Alternatively, integrate the system into the server framework of your choice.

Testing & validation

You can list tools via the included clients:

node scripts/test-streamable-http-client.mjs http://localhost:3000

Or for SSE transport:

node scripts/test-client.mjs http://localhost:3000

To manually call the tool via Streamable HTTP, use a simple JSON-RPC request (replace the origin as needed):

curl -sS http://localhost:3000/mcp \\
  -H 'content-type: application/json' \\
  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/call\",\"params\":{\"name\":\"hello_world\",\"arguments\":{\"style\":\"friendly\"}}}'

Sample Client

scripts/test-client.mjs contains a sample client to try invocations.

node scripts/test-client.mjs https://mcp-on-vercel.vercel.app

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
Kagi MCP Server

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.

Official
Featured
Python
graphlit-mcp-server

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.

Official
Featured
TypeScript
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
E2B

E2B

Using MCP to run code via e2b.

Official
Featured