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
10.6K

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

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
14.2K
5 points
B
Better Icons
An MCP server and CLI tool that provides search and retrieval of over 200,000 icons, supports more than 150 icon libraries, and helps AI assistants and developers quickly obtain and use icons.
TypeScript
8.5K
4.5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
16.4K
5 points
C
Claude Context
Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.
TypeScript
30.5K
5 points
A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
24.2K
5 points
M
MCP
The Microsoft official MCP server provides search and access functions for the latest Microsoft technical documentation for AI assistants
15.7K
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
12.8K
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
18.3K
4 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
37.5K
5 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
23.8K
4.5 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
26.1K
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
78.6K
4.3 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#
36.7K
5 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
69.3K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
23.0K
4.5 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
54.3K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase