Searxng MCP Server
S

Searxng MCP Server

This is an MCP server implementation project based on SearXNG, providing privacy - protected search capabilities for AI agents. The project is deployed through Docker containerization, supports two transport protocols, SSE and Stdio, and can be easily integrated into MCP - compatible clients.
2.5 points
5.7K

What is the SearXNG MCP Server?

This is a server based on the Model Context Protocol (MCP), specifically designed to provide privacy - protected web search functionality for AI agents. It uses the open - source SearXNG search engine as the backend, allowing AI assistants to perform web queries securely without revealing user privacy.

How to use the SearXNG MCP Server?

You can connect the server to MCP - compatible AI clients (such as Claude Desktop or Windsurf) through simple configuration. The server supports two connection methods: SSE (Server - Sent Events) and Stdio (Standard Input/Output).

Use cases

Suitable for scenarios where AI assistants are required for web searches but privacy protection is emphasized, such as personal knowledge management, research assistance, information verification, etc. It is particularly suitable for replacing traditional search engine APIs in privacy - sensitive environments.

Main features

Privacy - protected search
Provide a privacy - protected search service that does not track users or record queries through SearXNG
MCP protocol integration
Fully compatible with the Model Context Protocol and can be seamlessly integrated with various MCP clients
Multiple transport protocols
Support two communication methods, SSE and Stdio, to adapt to different deployment environments
Docker containerization
Provide a Docker image to simplify the deployment and management process
Advantages
Protect user privacy and do not record search queries
Open - source and self - hosted, with full control over data flow
Support multiple search parameters and filtering conditions
Lightweight and easy to deploy
Limitations
Need to maintain the SearXNG instance by yourself
The search speed may be slightly slower than that of commercial search engine APIs
Some advanced search functions may be restricted

How to use

Set up the SearXNG server
First, you need to run a SearXNG instance, which can be quickly deployed using Docker
Deploy the MCP server
You can choose to use Docker or directly run the Python script
Configure the MCP client
Add the MCP server configuration to your AI client and select the SSE or Stdio connection method

Usage examples

Academic research assistance
The AI assistant searches for the latest academic papers and research results through the MCP server
Fact - checking
Verify the accuracy of specific facts or data

Frequently Asked Questions

Why choose SearXNG instead of directly using the Google or Bing API?
How to improve the accuracy of search results?
What search parameters does the server support?

Related resources

SearXNG official documentation
The official documentation of the SearXNG search engine
Model Context Protocol specification
The official specification document of the MCP protocol
GitHub repository
Project source code

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "searxng": {
      "transport": "sse",
      "url": "http://localhost:32769/sse"
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "transport": "sse",
      "serverUrl": "http://localhost:32769/sse"
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "command": "python",
      "args": ["dev/searXNG-mcp/server.py"],
      "env": {
        "TRANSPORT": "stdio",
        "SEARXNG_BASE_URL": "http://localhost:32768",
        "HOST": "0.0.0.0",
        "PORT": "32769"
      }
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "command": "docker",
      "args": ["run", "--rm", "-i",
               "-e", "TRANSPORT",
               "-e", "SEARXNG_BASE_URL",
               "-e", "HOST",
               "-e", "PORT",
               "mcp/searxng-mcp"],
      "env": {
        "TRANSPORT": "stdio",
        "SEARXNG_BASE_URL": "http://localhost:32768",
        "HOST": "0.0.0.0",
        "PORT": "32769"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
9.7K
5 points
A
Annas MCP
The MCP server and CLI tool of Anna's Archive are used to search for and download documents on the platform and support access through an API key.
Go
6.7K
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
15.7K
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
46.5K
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
16.6K
4 points
M
Modelcontextprotocol
Certified
This project is an implementation of an MCP server integrated with the Sonar API, providing real-time web search capabilities for Claude. It includes guides on system architecture, tool configuration, Docker deployment, and multi-platform integration.
TypeScript
14.8K
5 points
B
Bilibili MCP Js
Certified
A Bilibili video search server based on the Model Context Protocol (MCP), providing API interfaces to support video content search, paginated queries, and video information return, including LangChain call examples and test scripts.
TypeScript
15.9K
4.2 points
P
Perplexity MCP
Certified
An MCP server based on the Perplexity AI API, providing web search functionality for the Claude desktop client.
Python
15.8K
4.1 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
15.0K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
24.0K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
17.0K
4.3 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
46.5K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
45.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
20.6K
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
31.1K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
64.7K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase