LLM Search
Verified IntegrationClient Configuration
— Connect LLM Search to Claude Desktop or Cursor in seconds{
"mcpServers": {
"llm-search": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-llm-search"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Empower local LLMs with real-time internet search capabilities, utilizing a self-hosted SearXNG instance and a FastAPI middleware for popular LLM backends.
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for LLM Search
LLM Search empowers your local Large Language Models (LLMs) with real-time internet search capabilities. It bundles a self-hosted SearXNG instance with a FastAPI middleware, allowing your LLM to perform web searches without needing any third-party API keys, rate limits, or signups.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.