Script runner for LLM Benchmark project
Script runner for LLM Benchmark project.
A Model Context Protocol (MCP) server that provides web search capabilities using SearxNG, allowing AI assistants like Claude to search the web.
This project implements an MCP server that connects to SearxNG, a privacy-respecting metasearch engine. The server provides a simple and efficient way for Large Language Models to search the web without tracking users.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"searxng": {
"command": "pipx",
"args": [
"run",
"searxng-simple-mcp@latest"
],
"env": {
"SEARXNG_MCP_SEARXNG_URL": "https://your-instance.example.com"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| SEARXNG_MCP_SEARXNG_URL | Declared in the maintainer’s client configuration. | Check documentation |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
An MCP (Model Context Protocol) server that helps you discover, identify, and govern every bot interacting with your website — search engines, AI crawlers, SEO tools, social-preview fetchers…
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Or with Docker Compose: ```sh docker compose --profile service up -d ```
MCP server for Google Search Console & Indexing API — search analytics, sitemaps, URL inspection