What services are currently implemented?
GitHub MCP (repositories, issues, pull requests) and Web MCP (web search, URL content). The structure is extensible to add more MCP services.
@lrdspc
Basic information
Servidor MCP centralizado hospedado no Vercel
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-server-hub": {
"type": "http",
"url": "https://mcp-server-hub.vercel.app/api/mcp"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list directly from this server's endpoint using the button above.
MCP Server Hub is a centralized Model Context Protocol (MCP) server hosted on Vercel. It enables AI models such as Claude and ChatGPT to interact with external services through a unified MCP endpoint. The server currently integrates with GitHub (repositories, issues, pull requests) and web search/URL content retrieval, and is built to be extensible for additional MCP servers.
Connect any MCP client (Claude Desktop, VS Code, etc.) to the URL https://mcp-server-hub.vercel.app/api/mcp. For local testing, clone the repository, run npm install, create a .env.local file with the required variables, and execute npm run dev — the server will be available at http://localhost:3000/api/mcp. Deploy on Vercel by importing the repo and setting the environment variables GITHUB_TOKEN (required) and SEARCH_API_KEY (optional). Configuration examples in JSON are provided for VS Code and other MCP clients.
GitHub MCP (repositories, issues, pull requests) and Web MCP (web search, URL content). The structure is extensible to add more MCP services.
Open VS Code settings, add the following to your JSON configuration: `{ "mcp": { "servers": { "github": { "url": "https://mcp-server-hub.vercel.app/api/mcp" } } } }`.
`GITHUB_TOKEN` is required (a GitHub personal access token with proper permissions). `SEARCH_API_KEY` is optional, depending on the search provider used.
Yes. Clone the repository, run `npm install`, create a `.env.local` file with the required variables, then run `npm run dev`. The server will be available at `http://localhost:3000/api/mcp`.
Fork the repository, import it into Vercel as a new project, set the environment variables (`GITHUB_TOKEN` and optionally `SEARCH_API_KEY`), and click Deploy. The resulting URL becomes your MCP endpoint.
PickFu MCP is a Model Context Protocol (MCP) server that connects AI assistants, developers, marketers, product managers, and AI agents to PickFu's consumer research platform. It enables users to create surveys, conduct
A search tool helps dev to solve the naming things problem.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Model Context Protocol Servers

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments