Fetch MCP Server

This MCP server fetches web content in HTML, JSON, plain text, and Markdown formats.

Components

Tools

• fetch_html: Fetches a website and returns its HTML content. Requires a url (string) and accepts optional headers (object).
• fetch_json: Fetches a JSON file from a URL. Requires a url (string) and accepts optional headers (object). Returns parsed JSON.
• fetch_txt: Fetches a website and returns plain text, stripping HTML tags, scripts, and styles. Requires a url (string) and accepts optional headers (object).
• fetch_markdown: Fetches a website and converts its content to Markdown format. Requires a url (string) and accepts optional headers (object).

Resources

The server fetches and transforms web content on demand without persistent resources.

Getting started

1. Clone the repository.
2. Install dependencies: npm install.
3. Build the server: npm run build.

Usage

Run the server: npm start. This starts the Fetch MCP Server on stdio.

Usage with Desktop App

Integrate with a desktop app using the provided JSON configuration, specifying the path to dist/index.js.

Features

• Uses the fetch API.
• Supports custom headers.
• Provides content in HTML, JSON, plain text, and Markdown.
• Uses JSDOM for HTML parsing and text extraction.
• Uses TurndownService for HTML to Markdown conversion.

Development

• npm run dev: Starts the TypeScript compiler in watch mode.
• npm test: Runs the test suite.

License

This project is licensed under the MIT License.