Fetch

v1.1.2Search & Data Extractionstable

Enables fetching and converting web content into various formats including HTML, JSON, plain text, and Markdown. It supports custom request headers and provides specialized tools for on-demand web data retrieval and transformation.

mcpfetchwebscrapemarkdown
Share:
761
Stars
0
Downloads
0
Weekly
0/5

What is Fetch?

Fetch is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables fetching and converting web content into various formats including html, json, plain text, and markdown. it supports custom request headers and provides specialized tools for on-demand web dat...

Enables fetching and converting web content into various formats including HTML, JSON, plain text, and Markdown. It supports custom request headers and provides specialized tools for on-demand web data retrieval and transformation.

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables fetching and converting web content into various for

Use Cases

Fetch and convert web content to HTML, JSON, plain text, or Markdown formats. Extract YouTube transcripts and clean webpage content. Retrieve and transform web data with custom headers on demand.
zcaceres

Maintainer

LicenseMIT License
Languagetypescript
Versionv1.1.2
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

NPM

npx -y mcp-fetch-server

Manual Installation

npx -y mcp-fetch-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Fetch

The Fetch MCP Server enables fetching and converting web content into HTML, JSON, plain text, and Markdown formats with support for custom headers and specialized YouTube transcript extraction. By connecting it to Claude, you unlock seamless web content retrieval and transformation for document analysis, research, and data extraction tasks.

Prerequisites

  • Node.js 18+ installed
  • An MCP client such as Claude Desktop or Cursor
  • Internet access for fetching web content
  • Optional: API keys for services requiring authentication
1

Install Fetch MCP Server

Install the mcp-fetch-server package via npm.

npx -y mcp-fetch-server
2

Add to MCP Configuration

Register the Fetch server in your client configuration.

{
  "mcpServers": {
    "fetch-mcp-server": {
      "command": "npx",
      "args": ["-y", "mcp-fetch-server"]
    }
  }
}
3

Configure Optional Headers or Authentication

If you need to fetch from services requiring authentication, set custom headers or API keys in environment variables.

4

Restart Client

Restart Claude Desktop or your MCP client to activate the Fetch server.

5

Start Fetching Web Content

Ask Claude to fetch and convert web pages, extract YouTube transcripts, or retrieve and parse web data.

Fetch Examples

Installation and Configuration

How to set up the Fetch MCP Server in Claude Desktop.

npx -y mcp-fetch-server
# Add to claude_desktop_config.json:
{
  "mcpServers": {
    "fetch-mcp-server": {
      "command": "npx",
      "args": ["-y", "mcp-fetch-server"]
    }
  }
}

Prompts to Try

Use these prompts to fetch and process web content with Claude.

1. "Fetch the GitHub repository README and summarize it in Markdown"
2. "Extract the transcript from this YouTube video URL and summarize key points"
3. "Fetch this webpage and convert it to JSON format for data extraction"

Troubleshooting Fetch

Fetch fails with connection error

Verify you have internet connectivity. Check that the URL is valid and accessible. Some sites may block automated requests; try adding custom User-Agent headers.

YouTube transcripts are not extracting correctly

Ensure the video URL is valid and the video has captions available. Try using the full YouTube URL. Check the Fetch server documentation for supported video formats.

Frequently Asked Questions about Fetch

What is Fetch?

Fetch is a Model Context Protocol (MCP) server that enables fetching and converting web content into various formats including html, json, plain text, and markdown. it supports custom request headers and provides specialized tools for on-demand web data retrieval and transformation. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Fetch?

Install via npm with the command: npx -y mcp-fetch-server. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).

Which AI clients work with Fetch?

Fetch works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Fetch free to use?

Yes, Fetch is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "fetch-mcp-server": { "command": "npx", "args": ["-y", "mcp-fetch-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Fetch?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides