How do I install the searchfetch mcp server?

Run it through your MCP client's configuration using `npx -y searchfetch`. Add the server block to Claude Desktop's config file (or use `claude mcp add` for Claude Code), restart the client, and the tools appear automatically. Full snippets are on this page.

Does the searchfetch mcp server need an API key?

No API key is documented for this server, so it should start without additional credentials. Because it runs locally, it inherits whatever access your machine already has — worth keeping in mind when you decide what to point it at.

Searchfetch MCP Server — Features, Setup & Tools

Name: Searchfetch MCP Server
Author: maxymlev

What is the Searchfetch MCP server?

Connect Searchfetch to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Fault-tolerant MCP Server for Stealth Web Search and Fetching. The searchfetch mcp server is what makes that connection.

What the server does

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.

Stealth Engine: — Powered by CloakBrowser C++ patches + humanize logic. The browser renders and moves like a real user, reducing bot-detection scores
Fault Tolerance: — Auto-healing browser sessions, grace-period timeouts for SPAs, and network-level blocking of tracking scripts and media
Token-Optimized Output: — Strips base64 images, SVGs, scripts, and inline styles from the DOM before Markdown conversion
Dual Runtime: — Natively supports zero-install execution via both Python (uvx) and Node.js (npx)
Template-Driven Extraction: — Structured extraction via shared JSON templates (GitHub, npm, PyPI, crates.io, docs pages, Docker Hub, and more). Supports custom inline templates

Installation

searchfetch on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

Where it fits

Among the browser automation options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. It is maintained by maxymlev; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Worth knowing first

It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How to install the Searchfetch MCP server

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

Configuration as documented by the project. Restart the client after saving.

Frequently asked questions

It connects Searchfetch to MCP-compatible AI assistants such as Claude and Cursor. Instead of copying data back and forth by hand, the assistant works with Searchfetch directly.

Searchfetch MCP Server

What is the Searchfetch MCP server?

What the server does

Installation

Where it fits

Worth knowing first

How to install the Searchfetch MCP server

Frequently asked questions

Alternatives to the Searchfetch MCP server

Playwright

Firecrawl

Puppeteer

Chrome DevTools

Browser MCP

Browserbase

Searchfetch MCP Server

What is the Searchfetch MCP server?

What the server does

Installation

Where it fits

Worth knowing first

How to install the Searchfetch MCP server

Frequently asked questions

What does the searchfetch mcp server do?

How do I install the searchfetch mcp server?

Does the searchfetch mcp server need an API key?

Alternatives to the Searchfetch MCP server

Playwright

Firecrawl

Puppeteer

Chrome DevTools

Browser MCP

Browserbase