mcp server fetch typescript

Local 2025-08-31 23:15:54 0
Browser Automation @tatn/mcp-server-fetch-typescript

A Model Context Protocol server that provides web content fetching and conversion capabilities.

A Model Context Protocol server that provides web content fetching and conversion capabilities. This server implements a comprehensive web content retrieval system with support for various formats and rendering methods, making it ideal for tasks ranging from simple data extraction to sophisticated web scraping.

Server Fetch TypeScript MCP server

Features

Tools

  • get_raw_text - Retrieve raw text content directly from URLs
  • Takes url as a required parameter pointing to text-based resources
  • Returns unprocessed text content without browser rendering
  • Ideal for JSON, XML, CSV, TSV, or plain text files

  • Best used when fast, direct access to source content is needed

  • get_rendered_html - Fetch fully rendered HTML content

  • Takes url as a required parameter
  • Returns complete HTML content after JavaScript execution
  • Uses Playwright for headless browser rendering

  • Essential for modern web applications and SPAs

  • get_markdown - Convert web content to Markdown format

  • Takes url as a required parameter
  • Returns well-formatted Markdown preserving structural elements
  • Supports tables and definition lists

  • Recommended for content archiving and documentation

  • get_markdown_summary - Extract and convert main content

  • Takes url as a required parameter
  • Returns clean Markdown focusing on main content
  • Automatically removes navigation, headers, footers
  • Perfect for article and blog post extraction

Installation

As a Global Package

npm install -g mcp-server-fetch-typescript

As a Project Dependency

npm install mcp-server-fetch-typescript

Usage

Using with Claude Desktop

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

"mcpServers": {
  "mcp-server-fetch-typescript": {
    "command": "npx",
    "args": [
      "-y",
      "mcp-server-fetch-typescript"
    ]
  }
}

or Add the following configuration:

git clone https://github.com/tatn/mcp-server-fetch-typescript.git
cd mcp-server-fetch-typescript
npm install
npm run build
"mcpServers": {
  "mcp-server-fetch-typescript": {
    "command": "node",
    "args": [
      "/path/to/mcp-server-fetch-typescript/build/index.js"
    ]
  }
}

Debugging

To debug the MCP server:

npx @modelcontextprotocol/inspector npx -y mcp-server-fetch-typescript
npx @modelcontextprotocol/inspector node /path/to/mcp-server-fetch-typescript/build/index.js
[
  {
    "description": "Retrieves raw text content directly from a URL without browser rendering. Ideal for structured data formats like JSON, XML, CSV, TSV, or plain text files. Best used when fast, direct access to the source content is needed without processing dynamic elements.",
    "inputSchema": {
      "properties": {
        "url": {
          "description": "URL of the target resource containing raw text content (JSON, XML, CSV, TSV, plain text, etc.).",
          "type": "string"
        }
      },
      "required": [
        "url"
      ],
      "type": "object"
    },
    "name": "get_raw_text"
  },
  {
    "description": "Fetches fully rendered HTML content using a headless browser, including JavaScript-generated content. Essential for modern web applications, single-page applications (SPAs), or any content that requires client-side rendering to be complete.",
    "inputSchema": {
      "properties": {
        "url": {
          "description": "URL of the target web page that requires JavaScript execution or dynamic content rendering.",
          "type": "string"
        }
      },
      "required": [
        "url"
      ],
      "type": "object"
    },
    "name": "get_rendered_html"
  },
  {
    "description": "Converts web page content to well-formatted Markdown, preserving structural elements like tables and definition lists. Recommended as the default tool for web content extraction when a clean, readable text format is needed while maintaining document structure.",
    "inputSchema": {
      "properties": {
        "url": {
          "description": "URL of the web page to convert to Markdown format, supporting various HTML elements and structures.",
          "type": "string"
        }
      },
      "required": [
        "url"
      ],
      "type": "object"
    },
    "name": "get_markdown"
  },
  {
    "description": "Extracts and converts the main content area of a web page to Markdown format, automatically removing navigation menus, headers, footers, and other peripheral content. Perfect for capturing the core content of articles, blog posts, or documentation pages.",
    "inputSchema": {
      "properties": {
        "url": {
          "description": "URL of the web page whose main content should be extracted and converted to Markdown.",
          "type": "string"
        }
      },
      "required": [
        "url"
      ],
      "type": "object"
    },
    "name": "get_markdown_summary"
  }
]