Skip to main content
MCP Server
Fetch avatar

Fetch

by @modelcontextprotocol

Official Install with VS Code GitHub

Web content fetching and conversion for efficient LLM usage

Share
fetchwebscrapinghtmlmarkdownhttp
890 stars TypeScript MIT Updated: 2025-05-08

Send to Your Agent

Copy this prompt and paste it into Claude, Cursor, or any MCP client to install instantly.

Install the Fetch MCP server for me.

Server: Fetch
Description: Web content fetching and conversion for efficient LLM usage
Install command: npx -y @modelcontextprotocol/server-fetch

GitHub: https://github.com/modelcontextprotocol/servers/tree/main/src/fetch

Please install this MCP server and confirm when ready.

Paste into any AI agent with MCP support — works with Claude Desktop, Cursor, Cline, and more.

Quick Install

Config file: ~/Library/Application Support/Claude/claude_desktop_config.json

  1. Open Claude Desktop app
  2. Go to Settings → Developer → Edit Config
  3. Paste the config below into the file
  4. Restart Claude Desktop
{
  "mcpServers": {
    "fetch": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-fetch"
      ]
    }
  }
}

Add this to your ~/Library/Application Support/Claude/claude_desktop_config.json

Installation Methods

npx Run directly with npx
npx -y @modelcontextprotocol/server-fetch
uvx Run with uvx (Python)
uvx mcp-server-fetch
pip Install via pip
pip install mcp-server-fetch

Tools (2)

fetch

Fetches a URL from the internet and extracts its contents as markdown

fetch_raw

Fetches a URL and returns raw content without markdown conversion

Compatibility

Claude Desktop
Cursor
Cline
VS Code
Devin (formerly Windsurf)

About

A Model Context Protocol server that provides web content fetching capabilities. This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.

Key Features

  • HTML to Markdown conversion — Clean, readable content extraction
  • Chunked reading — Use start_index to read large pages in chunks
  • Raw mode — Get unprocessed content when needed
  • Length control — Limit response size with max_length parameter

Tools

fetch

Fetches a URL and extracts its contents as markdown.

  • url (string, required): URL to fetch
  • max_length (integer, optional): Maximum characters to return (default: 5000)
  • start_index (integer, optional): Start content from this character index (default: 0)
  • raw (boolean, optional): Get raw content without markdown conversion (default: false)

Use Cases

  • Research — "Fetch the latest article from this URL and summarize it"
  • Documentation reading — "Get the README from this GitHub repo"
  • Content analysis — "Extract all links from this page"
  • Data collection — "Fetch pricing information from competitor websites"

Security Note

This server can access local/internal IP addresses. Exercise caution when using it to ensure sensitive data is not exposed.

Related Resources

Brave Search

MCP Server

Web and local search using Brave's Search API

Modern HTML Semantic Architect

Prompt

Build accessible, SEO-optimized HTML with proper semantic structure, ARIA attributes, and modern best practices.

Playwright E2E Testing Expert

Skill

Create comprehensive end-to-end tests using Playwright for web applications. Write reliable, maintainable test suites with proper page objects, fixtures, and CI/CD integration.

Artificial Intelligence

Glossary

The broad field of creating machines that can perform tasks requiring human-like intelligence, such as reasoning, learning, and perception.

arjunkmrm-fetch

MCP Server

Fetch web pages and extract exactly the content you need. Select elements with CSS and retrieve co…

Compare LLM Pricing

This server works with Claude, GPT-4o, and other models. Compare API costs side-by-side to find the cheapest option for your workflow.

Browse Pricing Compare Models Cost Calculator