Web Fetch
Fetches and converts web content, ideal for data extraction and web scraping.
mcp-server-fetch-typescript MCP Server
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.
Features
Tools
-
get_raw_text- Retrieve raw text content directly from URLs- Takes
urlas 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
- Takes
-
get_rendered_html- Fetch fully rendered HTML content- Takes
urlas a required parameter - Returns complete HTML content after JavaScript execution
- Uses Playwright for headless browser rendering
- Essential for modern web applications and SPAs
- Takes
-
get_markdown- Convert web content to Markdown format- Takes
urlas a required parameter - Returns well-formatted Markdown preserving structural elements
- Supports tables and definition lists
- Recommended for content archiving and documentation
- Takes
-
get_markdown_summary- Extract and convert main content- Takes
urlas a required parameter - Returns clean Markdown focusing on main content
- Automatically removes navigation, headers, footers
- Perfect for article and blog post extraction
- Takes
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
Похожие серверы
Bright Data
спонсорDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Configurable Puppeteer MCP Server
A configurable MCP server for browser automation using Puppeteer.
DidItChange
MCP-native website monitoring with AI-powered change summaries and natural conversation control.
Decodo
Easy web data access. Simplified retrieval of information from websites and online sources.
MCP Deep Web Research Server
An advanced web research server with intelligent search queuing, enhanced content extraction, and deep research capabilities.
NBA Player Stats
Provides comprehensive NBA player statistics from basketball-reference.com, including career stats, season comparisons, and advanced metrics.
Fetcher MCP
Fetch and extract web content using a Playwright headless browser, with support for intelligent extraction and flexible output.
Opengraph.io
Opengraph data, web scraping, screenshot features in a handy MCP tool
GitPrism
GitPrism is a fast, token-efficient, stateless pipeline that converts public GitHub repositories into LLM-ready Markdown.
just-every/mcp-screenshot-website-fast
High-quality screenshot capture optimized for Claude Vision API. Automatically tiles full pages into 1072x1072 chunks (1.15 megapixels) with configurable viewports and wait strategies for dynamic content.
Patchright Lite MCP Server
A server that wraps the Patchright SDK to provide stealth browser automation for AI models.