Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AIFire in da houseCheck it out free

MCP-searxng

MCP.Pizza Chef: SecretiveShell

MCP-searxng is an MCP server designed to connect agentic AI systems to web search capabilities through the searXNG search engine. It allows models and agents to perform real-time, privacy-respecting web searches by sending queries to searXNG and retrieving structured search results. This server integrates seamlessly with MCP clients using simple JSON configuration or direct command-line invocation, enabling enhanced context gathering and information retrieval for AI workflows. MCP-searxng supports flexible deployment via uvx or local cloning, making it a versatile tool for augmenting AI agents with powerful search functionality.

Use This MCP server To

Enable AI agents to perform real-time web searches Integrate privacy-focused search into AI workflows Retrieve structured search results for context enrichment Augment language models with external search data Connect agentic systems to searXNG search engine Support multi-step reasoning with live search queries

README

MCP-searxng

An MCP server for connecting agentic systems to search systems via searXNG.

MCP SearxNG Badge

Tools

Search the web with SearXNG

Prompts

search(query: str) -> f"Searching for {query} using searXNG"

Usage

via uvx

  1. configure your client JSON like
{
  "mcpServers": {
    "searxng": {
      "command": "uvx", 
      "args": [
        "mcp-searxng"
      ]
    }
  }
}

via git clone

  1. Add the server to claude desktop (the entrypoint is main.py)

Clone the repo and add this JSON to claude desktop

you can run this server with uvx mcp-searxng, or use a local copy of the repo

{
  "mcpServers": {
    "searxng": {
      "command": "uv", 
      "args": [
        "--project",
        "/absoloute/path/to/MCP-searxng/",
        "run",
        "/absoloute/path/to/MCP-searxng/mcp-searxng/main.py"
      ]
    }
  }
}

you will need to change the paths to match your environment

Custom SearXNG URL

  1. set the environment variable SEARXNG_URL to the URL of the searxng server (default is http://localhost:8080)

  2. run your MCP client and you should be able to search the web with searxng

Note: if you are using claude desktop make sure to kill the process (task manager or equivalent) before running the server again

MCP-searxng FAQ

How do I configure MCP-searxng with an MCP client?
Configure your client JSON to include the MCP-searxng server with the command 'uvx' and appropriate arguments, or clone the repo and run it locally with 'uvx mcp-searxng'.
Can MCP-searxng be run locally?
Yes, you can clone the MCP-searxng repository and run the server locally using the provided entrypoint 'main.py' with uvx or uv commands.
What search engine does MCP-searxng use?
MCP-searxng uses searXNG, a privacy-respecting, open-source metasearch engine, to perform web searches.
Is MCP-searxng compatible with multiple MCP clients?
Yes, MCP-searxng is designed to work with any MCP client that supports server integration via JSON configuration or command-line invocation.
How does MCP-searxng improve AI agent capabilities?
By enabling real-time web search queries, MCP-searxng allows AI agents to access up-to-date information beyond their training data, enhancing reasoning and response accuracy.
Does MCP-searxng support custom search queries?
Yes, you can send any search query string to MCP-searxng, which will forward it to searXNG and return the results.
What are the deployment options for MCP-searxng?
MCP-searxng can be deployed via the uvx command-line tool or by cloning the repository and running it locally, providing flexibility for different environments.
Can MCP-searxng be integrated with AI models from OpenAI, Claude, or Gemini?
Yes, MCP-searxng can be integrated with AI models from OpenAI, Anthropic Claude, and Google Gemini through MCP clients to enhance their search capabilities.