MCP cover image
See in Github
2025-02-26

提供Web内容获取功能的模型上下文协议服务器。

1

Github Watches

1

Github Forks

5

Github Stars

Fetch MCP Server

A port of the official Fetch MCP Server for Node.js. Please check the key differences with original project section for more details.

Description

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.

The fetch tool will truncate the response, but by using the start_index argument, you can specify where to start the content extraction. This lets models read a webpage in chunks, until they find the information they need.

Available Tools

  • fetch - Fetches a URL from the internet and extracts its contents as markdown.
    • url (string, required): URL to fetch
    • max_length (integer, optional): Maximum number of 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)

Available Prompts

  • fetch - Fetch a URL and extract its contents as markdown
    • url (string, required): URL to fetch

Usage

mcp-fetch-node exposes an SSE endpoint at /sse on port 8080 by default.

Node.js:

npx -y mcp-fetch-node

Docker:

docker run -it tgambet/mcp-fetch-node

Customization - robots.txt

By default, the server will obey a websites robots.txt file if the request came from the model (via a tool), but not if the request was user initiated (via a prompt). This can be disabled by adding the argument --ignore-robots-txt to the run command.

Customization - User-agent

By default, depending on if the request came from the model (via a tool), or was user initiated (via a prompt), the server will use either the user-agent

# Tool call
ModelContextProtocol/1.0 (Autonomous; +https://github.com/tgambet/mcp-fetch-node)

# Prompt
ModelContextProtocol/1.0 (User-Specified; +https://github.com/tgambet/mcp-fetch-node)

This can be customized by adding the argument --user-agent=YourUserAgent to the run command, which will override both.

Key differences with the original project

  • This implementation is written in TypeScript and targets the Node.js runtime. It is suited for situations where python is not available.

  • This implementation provides an SSE interface instead of stdio. It is more suitable for deployment as a web service, increasing flexibility.

  • This implementation does not rely on Readability.js library for content extraction. It uses a custom implementation that is more generic and suited for websites other that news-related ones.

The api and tool description is, however, the same as the original project so you can try mcp-fetch-node as a drop-in replacement for the original project.

Please report any issue to the issue tracker.

Features

  • Fetch and extract relevant content from a URL
  • Respect robots.txt (can be disabled)
  • User-Agent customization
  • Markdown conversion
  • Pagination

Development

pnpm install
pnpm dev
pnpm lint:fix
pnpm format
pnpm test
pnpm build
pnpm start
pnpm inspect

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT

TODO

相关推荐

  • NiKole Maxwell
  • I craft unique cereal names, stories, and ridiculously cute Cereal Baby images.

  • Bora Yalcin
  • Evaluator for marketplace product descriptions, checks for relevancy and keyword stuffing.

  • https://jgadvisorycpa.com
  • This GPT assists in finding a top-rated business CPA - local or virtual. We account for their qualifications, experience, testimonials and reviews. Business operators provide a short description of your business, services wanted, and city or state.

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Alexandru Strujac
  • Efficient thumbnail creator for YouTube videos

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • apappascs
  • 发现市场上最全面,最新的MCP服务器集合。该存储库充当集中式枢纽,提供了广泛的开源和专有MCP服务器目录,并提供功能,文档链接和贡献者。

  • ShrimpingIt
  • MCP系列GPIO Expander的基于Micropython I2C的操作,源自ADAFRUIT_MCP230XX

  • OffchainLabs
  • 进行以太坊的实施

  • modelcontextprotocol
  • 模型上下文协议服务器

  • huahuayu
  • 统一的API网关,用于将多个Etherscan样区块链Explorer API与对AI助手的模型上下文协议(MCP)支持。

  • Mintplex-Labs
  • 带有内置抹布,AI代理,无代理构建器,MCP兼容性等的多合一桌面和Docker AI应用程序。

    Reviews

    4 (1)
    Avatar
    user_ODhGg02I
    2025-04-17

    As a dedicated user of mcp-fetch-node, I am thoroughly impressed by its efficiency and ease of use. The documentation provided by tgambet is comprehensive, making the integration process seamless. Whether for retrieving data from various nodes or powering complex applications, this product excels in performance and reliability. Highly recommended for developers looking to streamline their node-fetching processes! Check it out on GitHub for more details.