Fetch (Web Content & YouTube Transcripts) MCP server

Fetches web content and YouTube video transcripts, converting HTML to Markdown and extracting timestamps for reference in conversations.
Back to servers
Provider
EGOIST
Release date
Apr 01, 2025
Language
TypeScript
Package
Stats
29.7K downloads
152 stars

This MCP server allows you to fetch URLs and YouTube video transcripts, providing these capabilities through various server types including stdio, SSE, and HTTP. The server is built for integration with Large Language Models that support the Model Context Protocol.

Installation

The fetch-mcp server can be run directly using npx without requiring a permanent installation. This makes it easy to use the tool without adding it to your project dependencies.

npx -y fetch-mcp

Server Types

You can run the MCP server in different modes depending on your needs:

Standard I/O Server

Run the server with standard input/output:

npx -y fetch-mcp

Server-Sent Events (SSE) Server

Launch the server with SSE support:

npx -y fetch-mcp --sse

HTTP Server

Start an HTTP server that can stream responses:

# Default endpoint at /mcp
npx -y fetch-mcp --http

# Custom endpoint
npx -y fetch-mcp --http /my-mcp

Available Tools

The MCP server provides two main tools:

fetch_url

This tool allows you to fetch content from a URL. By default, it returns the content in Markdown format, but you can also retrieve the raw HTML.

Example usage:

  • Fetches the content at the specified URL
  • Can be configured to return HTML or Markdown (default)

fetch_youtube_transcript

This tool enables you to retrieve the transcript of a YouTube video.

Example usage:

  • Takes a YouTube video URL or ID as input
  • Returns the complete transcript text from the video

Both tools are accessible through the MCP interface and can be called by LLM systems that implement the Model Context Protocol.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later