Searchfetch - Mcp Server For Web Search And Fetching

Name: Searchfetch - Mcp Server For Web Search And Fetching
Author: maxylev

@maxylev

About Searchfetch - Mcp Server For Web Search And Fetching

A maximum fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built specifically for AI Agents (Cursor, Claude Desktop, OpenHands), it completely bypasses bot detection (Cloudflare Turnstile, Datadome), dynamically handles S

#websearch #google-search

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "searchfetch": {
      "command": "uvx",
      "args": [
        "searchfetch"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Searchfetch?

Searchfetch is a maximum fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. It is built for AI Agents (Cursor, Claude Desktop, OpenHands) and bypasses bot detection, dynamically handles SPAs/React, and converts web content into token-optimized Markdown.

How to use Searchfetch?

Configure your MCP client (e.g., Claude Desktop, Cursor) to use the zero-install command uvx searchfetch (Python) or npx -y searchfetch (Node.js). Then use the provided tools: websearch to search the web via DuckDuckGo or Google, and webfetch to fetch and extract text content from any webpage.

Key features of Searchfetch

Maximum fault tolerance with auto-healing browser sessions.
Stealth engine that bypasses Cloudflare Turnstile and Datadome.
Nuclear Token Scrubber strips Base64 images, SVGs, and scripts.
Dual execution paths: Python (uvx) and Node.js (npx).
Supports both DuckDuckGo and Google search engines.
Outputs clean Markdown, clean HTML, or raw HTML.

Use cases of Searchfetch

Research general knowledge, news, and find URLs via web search.
Extract main text content from JavaScript-heavy single-page applications.
Fetch large documents with pagination via start_index and max_length.
Provide LLMs with token-optimized content by stripping media and scripts.

FAQ from Searchfetch

What runtimes does Searchfetch require?

Searchfetch can run via Python (uvx) or Node.js (npx), both with zero-install execution.

What search engines are supported?

Searchfetch supports DuckDuckGo and Google search engines.

Can Searchfetch handle JavaScript-heavy pages?

Yes, webfetch fully executes JavaScript to load React/SPAs before extracting content.

What output formats are available for fetched pages?

The webfetch tool supports markdown (default), clean_html, and raw_html formats.

How does Searchfetch avoid bot detection?

It uses CloakBrowser C++ patches and humanize logic to mathematically mimic a normal browser.

Comments

More Search MCP servers

Google Search Tool

web-agent-master

A Playwright-based Node.js tool that bypasses search engine anti-scraping mechanisms to execute Google searches. Local alternative to SERP APIs with MCP server integration.

611

mcp-omnisearch

spences10

🔍 A Model Context Protocol (MCP) server providing unified access to multiple search engines (Tavily, Brave, Kagi, Exa), AI tools (Kagi FastGPT, Exa, Linkup), and content extraction services (Firecrawl, Tavily, Kagi). Includes GitHub search. All through a single interface.

332