Searchfetch - MCP Server For Web Search And Fetching

@maxylev

Basic information

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

Searchfetch - MCP Server For Web Search And Fetching config

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

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

Searchfetch - MCP Server For Web Search And Fetching tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

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.

Frequently asked questions

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

SaaS Think Tank — Software Research

SaaS Think Tank

Software research to help people choose the right tools. SaaS Think Tank publishes software comparisons, reviews and practical resources across categories, with dated findings, source links and clear limits. Current MCP

Desearch

Desearch-ai

AI search, X search and web search for AI agents, plus page extraction and X data tools. Bring your own Desearch API key.

Vivu

Search your video library with natural language and retrieve relevant moments through MCP.

Lochless

Every match, not the top 10. Lochless is a hosted text index for LLM apps and agents. Send raw text through the API, then ask in plain English. It reads the documents in scope, up to a read limit you set, and returns eve

OpenCityRecord

OpenCity

Search city council meetings, votes, and documents across U.S. cities, with citations to the official record.