Docs Fetch MCP Server

A Model Context Protocol (MCP) server for fetching web content with recursive exploration capabilities. This server enables LLMs to autonomously explore web pages and documentation to learn about specific topics.

Overview

The Docs Fetch MCP Server provides a simple but powerful way for LLMs to retrieve and explore web content. It enables:

Fetching clean, readable content from any web page
Recursive exploration of linked pages up to a specified depth
Same-domain link traversal to gather comprehensive information
Smart filtering of navigation links to focus on content-rich pages

This tool is particularly useful when users want an LLM to learn about a specific topic by exploring documentation or web content.

Features

Content Extraction: Cleanly extracts the main content from web pages, removing distractions like navigation, ads, and irrelevant elements
Link Analysis: Identifies and extracts links from the page, assessing their relevance
Recursive Exploration: Follows links to related content within the same domain, up to a specified depth
Parallel Processing: Efficiently crawls content with concurrent requests and proper error handling
Robust Error Handling: Gracefully handles network issues, timeouts, and malformed pages
Dual-Strategy Approach: Uses fast axios requests first with puppeteer as a fallback for more complex pages
Timeout Prevention: Implements global timeout handling to ensure reliable operation within MCP time limits
Partial Results: Returns available content even when some pages fail to load completely

Usage

The server exposes a single MCP tool:

`fetch_doc_content`

Fetches web page content with the ability to explore linked pages up to a specified depth.

Parameters:

url (string, required): URL of the web page to fetch
depth (number, optional, default: 1): Maximum depth of directory/link exploration (1-5)

Returns:

{
  "rootUrl": "https://example.com/docs",
  "explorationDepth": 2,
  "pagesExplored": 5,
  "content": [
    {
      "url": "https://example.com/docs",
      "title": "Documentation",
      "content": "Main page content...",
      "links": [
        {
          "url": "https://example.com/docs/topic1",
          "text": "Topic 1"
        },
        ...
      ]
    },
    ...
  ]
}

Installation

Clone this repository:

git clone https://github.com/wolfyy970/docs-fetch-mcp.git
cd docs-fetch-mcp

Install dependencies:

npm install

Build the project:

npm run build

Configure your MCP settings in your Claude Client:

{
  "mcpServers": {
    "docs-fetch": {
      "command": "node",
      "args": [
        "/path/to/docs-fetch-mcp/build/index.js"
      ],
      "env": {
        "MCP_TRANSPORT": "pipe"
      }
    }
  }
}

Dependencies

@modelcontextprotocol/sdk: MCP server SDK
puppeteer: Headless browser for web page interaction
axios: HTTP client for making requests

Development

To run the server in development mode:

npm run dev

License

MIT

Install Server

HTTP connection URL

security – no known vulnerabilities

license - permissive license

quality - confirmed to work

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

fetch_doc_content

Enables LLMs to autonomously retrieve and explore web content by fetching pages and recursively following links to a specified depth, particularly useful for learning about topics from documentation.

Related MCP Servers

Fetch MCP Serverofficial
modelcontextprotocol
A
security
A
license
A
quality
This server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.
Last updated -
1
61,341
TypeScript
MIT License
MCP JinaAI Reader Server
spences10
A
security
A
license
A
quality
Integrates Jina.ai's Reader API with LLMs for efficient and structured web content extraction, optimized for documentation and web content analysis.
Last updated -
1
568
30
JavaScript
MIT License
Fetch MCP Server
ExactDoug
-
security
A
license
-
quality
Enables retrieval and processing of web page content for LLMs by converting HTML to markdown, with support for content truncation and pagination.
Last updated -
1
1
Python
MIT License
Web Content MCP Server
amotivv
A
security
A
license
A
quality
A server that leverages Cloudflare Browser Rendering to extract and process web content for use as context in LLMs, offering tools for fetching pages, searching documentation, extracting structured content, and summarizing content.
Last updated -
4
7
TypeScript
MIT License

View all related MCP servers

Docs Fetch MCP Server