- Explore MCP Servers
- mcp-on-vercel
Mcp On Vercel
What is Mcp On Vercel
mcp-on-vercel is a boilerplate for running Remote MCP Servers on FaaS (Function as a Service) providers, specifically utilizing Vercel’s Hobby Tier for free serverless deployment.
Use cases
Use cases include running remote MCP servers for applications that require real-time data processing, enabling developers to test and deploy applications without managing physical servers.
How to use
To use mcp-on-vercel, fork the repository and connect it to your Vercel account. Deploy it to get your URL, install the MCP server using the provided self-hosted installer, and configure your client to connect to the remote server.
Key features
Key features include stateless Python MCP server functionality, serverless deployment on Vercel Functions, automatic configuration for clients, and optional API key authentication for secure access.
Where to use
mcp-on-vercel can be used in various fields such as software development, cloud computing, and remote application hosting, where serverless architecture is beneficial.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcp On Vercel
mcp-on-vercel is a boilerplate for running Remote MCP Servers on FaaS (Function as a Service) providers, specifically utilizing Vercel’s Hobby Tier for free serverless deployment.
Use cases
Use cases include running remote MCP servers for applications that require real-time data processing, enabling developers to test and deploy applications without managing physical servers.
How to use
To use mcp-on-vercel, fork the repository and connect it to your Vercel account. Deploy it to get your URL, install the MCP server using the provided self-hosted installer, and configure your client to connect to the remote server.
Key features
Key features include stateless Python MCP server functionality, serverless deployment on Vercel Functions, automatic configuration for clients, and optional API key authentication for secure access.
Where to use
mcp-on-vercel can be used in various fields such as software development, cloud computing, and remote application hosting, where serverless architecture is beneficial.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
Remote Serverless MCP Servers
You want to run a remote MCP server, but you don’t want to host or pay for a server. Well you’re in luck, you can use the Vercel Hobby Tier to run it for free.
This is an adapter library that provides a stateless Python MCP server that runs on Vercel Functions, enabling serverless deployment of MCP tools as edge functions with self-hosting installers.
Prerequisites
Fork this repo and connect it to your Vercel account. Once it’s deployed get the URL
(your-domain.vercel.app).
If you don’t have uv installed, install it from astral:
curl -LsSf https://astral.sh/uv/install.sh | sh
Then, install the MCP server using the self-hosted installer:
uv run https://your-domain.vercel.app/install.py
And we’re done. This automatically:
- Configures Claude Desktop and Cursor to use the MCP server
- Uses the bridge script served directly from the server
- No downloads or local files needed
Go to your client and type something stupid like “Use MCP to get the server time” and it should use the remote server.
Authentication (Optional)
The server supports optional API key authentication to restrict access. To enable authentication:
- Server-side: Set the
MCP_API_KEYenvironment variable in your Vercel deployment - Client-side: The installer will prompt for an API key during setup
You can set the API key in your vercel.json file or in the Vercel dashboard:
{
"env": {
"MCP_API_KEY": "your-secret-key-here"
}
}
When an API key is configured on the server, all MCP requests must include the key in the X-API-Key header. The bridge script automatically handles this when the MCP_API_KEY environment variable is set in the client configuration.
Local Development
uv sync
vercel dev
Deploy
You just push to Github and it should just work.
Or manually deploy:
vercel --prod
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.










