MCP SearxNG Search

An attempt at an MCP for searxng search specifically for Goose

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jay4242-mcp_searxng_search": {
      "command": "uv",
      "args": [
        "run",
        "/full/path/to/mcp-searxng-search/.venv/bin/mcp-searxng-search"
      ],
      "env": {
        "SEARXNG_BASE_URL": "https://your-searxng-instance.example.org"
      }
    }
  }
}

This MCP server lets you perform web searches through a SearxNG instance by exposing a reusable tool that other MCP-compatible applications can call, such as Goose. It streamlines searching from within chat or automation workflows and returns query results based on your configured SearxNG backend.

How to use

You integrate this MCP server with an MCP client to perform web searches via your SearxNG instance. Before you start, set the base URL for your SearxNG backend using the required environment variable SEARXNG_BASE_URL. Then call the available tool to submit a search query and receive results.

How to install

Prerequisites: you need Python and pip installed on your system.

Ensure Python 3.x is installed on your machine.
Install the MCP server package from your project directory.
Set the base URL for your SearxNG instance using SEARXNG_BASE_URL.
Run the MCP server using the provided runtime command.

uv run /full/path/to/mcp-searxng-search/.venv/bin/mcp-searxng-search

Additional notes

The tool exposed by this MCP server is identified as searxng_search. It accepts two parameters: query for the search query and max_results for the number of results to return (default 30). You can use this tool within MCP clients to fetch search results from your SearxNG backend.

Available tools

searxng_search

Search the web via the SearxNG instance. Parameters: query and max_results.