mcpField
S
SearXNG MCP Server

SearXNG MCP Server

Local
github.com/tisDDMSearch43Updated 40w ago

About SearXNG MCP Server

SearXNG MCP Server is an MCP server that lets AI assistants run web searches through the SearXNG metasearch engine. It works without extra deployment by picking a random public instance from SearX.space, and it also supports private instances with basic authentication.

Key features

  1. 01Zero-configuration use with a random public instance
  2. 02Connection to private SearXNG instances with basic auth
  3. 03Filters for language, time range, categories and engines
  4. 04Search results returned in Markdown format

Use cases

  1. 01Adding live web search to an AI assistant
  2. 02Running searches against a self-hosted SearXNG instance
  3. 03Finding recent news or results within a time range

MCP support

This project is an MCP server that exposes the searxngsearch tool to MCP clients for running SearXNG searches.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

SearXNG MCP Server

SearXNG MCP Logo

A Model Context Protocol (MCP) server that enables AI assistants to perform web searches using SearXNG, a privacy-respecting metasearch engine. Works out-of-the-box with zero additional deployment by automatically selecting a random instance from SearX.space, while also supporting private instances with basic authentication.

This project is deprecated. Its successor is searxNcrawl at https://github.com/DasDigitaleMomentum/searxNcrawl

Deprecated

This repository is deprecated in favor of searxNcrawl. The successor currently does not include round-robin instance selection (it is usually unreliable). If you file a suitable defect report, it can be added.

Features

  • Zero-configuration setup: Works immediately by using a random public instance from SearX.space
  • Private instance support: Connect to your own SearXNG instance with optional basic authentication
  • Perform web searches with customizable parameters
  • Support for multiple search engines
  • Privacy-focused search results
  • Markdown-formatted search results
  • Sensible default values for all parameters

CAVEAT - Public Instances might be unavailabe for this purpose and return "Request failed with status code 429"

Installation

Prerequisites
  • Node.js (v16 or higher)
  • npm (v7 or higher)
  • Access to a SearXNG instance (self-hosted or public)
Install from source
# Clone the repository
git clone https://github.com/tisDDM/searxng-mcp.git
cd searxng-mcp

# Install dependencies
npm install

# Build the project
npm run build

Configuration

The SearXNG MCP server can be configured with the following environment variables:

  • SEARXNG_URL (optional): The URL of your SearXNG instance (e.g., https://searx.example.com). If not provided, a random public instance from SearX.space will be automatically selected, making the server usable with zero additional deployment.
  • USE_RANDOM_INSTANCE (optional): Set to "false" to disable random instance selection when no URL is provided. Default is "true".
  • SEARXNG_USERNAME (optional): Username for basic authentication when connecting to a private instance
  • SEARXNG_PASSWORD (optional): Password for basic authentication when connecting to a private instance

You can set these environment variables in a .env file in the root directory of the project:

SEARXNG_URL=https://searx.example.com
SEARXNG_USERNAME=your_username
SEARXNG_PASSWORD=your_password

Usage

Running the server
# If installed globally
searxngmcp

# If installed from source
node build/index.js
Integrating with Claude Desktop
  1. Open Claude Desktop
  2. Go to Settings > MCP Servers
  3. Add a new MCP server with the following configuration:
    {
      "mcpServers": {
        "searxngmcp": {
          "command": "searxngmcp",
          "env": {
            // Optional: If not provided, a random public instance will be used
            "SEARXNG_URL": "https://searx.example.com",
            // Optional: Only needed for private instances with authentication
            "SEARXNG_USERNAME": "your_username",
            "SEARXNG_PASSWORD": "your_password"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }
    
Integrating with Claude in VSCode
  1. Open VSCode
  2. Go to Settings > Extensions > Claude > MCP Settings
  3. Add a new MCP server with the following configuration:
    {
      "mcpServers": {
        "searxngmcp": {
          "command": "node",
          "args": ["/path/to/searxng-mcp/build/index.js"],
          "env": {
            // Optional: If not provided, a random public instance will be used
            "SEARXNG_URL": "https://searx.example.com",
            // Optional: Only needed for private instances with authentication
            "SEARXNG_USERNAME": "your_username",
            "SEARXNG_PASSWORD": "your_password"
          },
          "disabled": false,
          "autoApprove": []
        }
      }
    }
    

Usage with Smolagents

SearXNG MCP can be easily integrated with Smolagents, a lightweight framework for building AI agents. This allows you to create powerful research agents that can search the web and process the results:

from smolagents import CodeAgent, LiteLLMModel, ToolCollection
from mcp import StdioServerParameters

# Configure the SearXNG MCP server
server_parameters = StdioServerParameters(
    command="node",
    args=["path/to/searxng-mcp/build/index.js"],
    env={
        "SEARXNG_URL": "https://your-searxng-instance.com",
        "SEARXNG_USERNAME": "your_username",  # Optional
        "SEARXNG_PASSWORD": "your_password"   # Optional
    }
)

# Create a tool collection from the MCP server
with ToolCollection.from_mcp(server_parameters) as tool_collection:
    # Initialize your LLM model
    model = LiteLLMModel(
        model_id="your-model-id",
        api_key="your-api-key",
        temperature=0.7
    )
    
    # Create an agent with the search tools
    search_agent = CodeAgent(
        name="search_agent",
        tools=tool_collection.tools,
        model=model
    )
    
    # Run the agent with a search prompt
    result = search_agent.run(
        "Perform a search about: 'climate change solutions' and summarize the top 5 results."
    )
    
    print(result)

Available Tools

searxngsearch

Perform web searches using SearXNG, a privacy-respecting metasearch engine. Returns relevant web content with customizable parameters.

Parameters
ParameterTypeDescriptionDefaultRequired
querystringSearch query-Yes
languagestringLanguage code for search results (e.g., 'en', 'de', 'fr')'en'No
time_rangestringTime range for search results. Options: 'day', 'week', 'month', 'year'nullNo
categoriesarray of stringsCategories to search in (e.g., 'general', 'images', 'news')nullNo
enginesarray of stringsSpecific search engines to usenullNo
safesearchnumberSafe search level: 0 (off), 1 (moderate), 2 (strict)1No
pagenonumberPage number for results. Must be minimum 11No
max_resultsnumberMaximum number of search results to return. Range: 1-5010No
Example
// Example request
const result = await client.callTool('searxngsearch', {
  query: 'climate change solutions',
  language: 'en',
  time_range: 'year',
  categories: ['general', 'news'],
  safesearch: 1,
  max_results: 5
});

Development

Setup
# Clone the repository
git clone https://github.com/tisDDM/searxng-mcp.git
cd searxng-mcp

# Install dependencies
npm install
Build
npm run build
Watch mode (for development)
npm run watch
Testing with MCP Inspector
npm run inspector

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.