# Fetch MCP Server

> Fetch MCP Server is an open-source MCP server for web search and scraping. Fetch web pages as markdown with SSRF protection, reader mode, feeds and robots checks. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI
- **Website:** https://yaw.sh/mcp-servers/fetch-mcp/
- **Repository:** https://github.com/yawlabs/fetch-mcp
- **MCP Registry name:** io.github.YawLabs/fetch-mcp
- **Categories:** web search and scraping, developer tools
- **Listing updated:** 2026-11-14

## About

Giving a model a raw HTTP client can double as a probe against your internal network. This server keeps SSRF protection on by default and refuses to dial private addresses and cloud metadata endpoints unless an allow_private_hosts setting is changed.

Pages come back in forms that fit a context window: markdown said to be 3-8x smaller than raw HTML, plain text with block structure, or reader mode that isolates the article body. Other tools return head metadata (OpenGraph, JSON-LD, feeds), classified outbound links, parsed sitemaps including gzipped indexes, RSS and Atom entries, and a robots.txt verdict for a path and user agent.

Write methods exist too, with JSON bodies, headers, retries and byte caps. It is MIT-licensed, installs from npm and needs no key.

## Features

- **SSRF guard:** Private hosts are blocked by default.
- **Reader mode:** Extracts the article body with title and clean markdown.
- **Structured parsers:** Metadata, links, sitemaps, feeds and robots.txt each have a tool.
- **Full HTTP verbs:** GET, HEAD, OPTIONS, POST, PUT, PATCH and DELETE with auth and timeouts.
- **Size and retry controls:** Byte caps flag truncation and retries honour Retry-After.

## Good for

- Summarise a documentation page without nav clutter
- Read OpenGraph and JSON-LD for a URL
- Enumerate a site's pages from its sitemap
- Check whether a path may be crawled
- Call a staging webhook and read the response

## Install

### Claude Code (Terminal)

```sh
claude mcp add fetch-mcp -- npx -y @yawlabs/fetch-mcp
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "fetch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/fetch-mcp"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "fetch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/fetch-mcp"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "fetch-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/fetch-mcp"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "fetch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/fetch-mcp"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "fetch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@yawlabs/fetch-mcp"
      ]
    }
  }
}
```

## Tools

- `http_get`: Bare GET request with headers, auth, timeout, size cap and retry.
- `http_head`: HEAD request with the shared parameter set.
- `http_options`: OPTIONS request with the shared parameter set.
- `http_post`: Write-method HTTP with a JSON or raw body.
- `http_put`: Write-method HTTP with a JSON or raw body.
- `http_patch`: Write-method HTTP with a JSON or raw body.
- `http_delete`: Write-method HTTP with a JSON or raw body.
- `fetch_html_to_markdown`: GET a page and convert it to clean markdown.
- `fetch_html_to_text`: GET a page and convert it to plain text with block structure preserved.
- `fetch_reader`: Reader-mode extraction returning title plus markdown.
- `fetch_meta`: Extract head metadata including OpenGraph, Twitter cards and JSON-LD.
- `fetch_links`: Every outbound link resolved to absolute URLs and classified internal or external.
- `fetch_sitemap`: Parse sitemap.xml including gzipped sitemaps and index chaining.
- `fetch_feed`: Parse an RSS 2.0 or Atom 1.0 feed into entries.
- `fetch_robots`: Return the robots.txt verdict for a path and user agent.

## FAQ

### Is an API key required?

No. The site says there is nothing to provision.

### How big are the markdown results?

The tool table says 3-8x smaller than raw HTML.

### What licence is it?

MIT, published on npm as @yawlabs/fetch-mcp.

### Is Fetch MCP Server free?

Yes. Fetch MCP Server is open source, so you can use and self-host it for free.

### How do I add Fetch MCP Server to Claude Code?

Run this command in your terminal: claude mcp add fetch-mcp -- npx -y @yawlabs/fetch-mcp

### What are the best alternatives to Fetch MCP Server?

The closest alternatives to Fetch MCP Server are REA, Scrapling MCP Server, Codebase Memory, GitHub and Serena MCP: the IDE for your agent.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/fetch-mcp-server
