AIbase
EN
Explore
MCP Searxng
M

MCP Searxng

An MCP server implementation integrating the SearXNG API, providing web search functions and supporting features such as pagination, time filtering, language selection, and safe search.
Search toolsArtificial intelligence chatbots#Web Search#Pagination Control#Safe Filtering Local.JavaScript
2.5 points
103

What is the SearXNG MCP Server?

The SearXNG MCP Server is a server implementation based on the Model Context Protocol (MCP), which integrates the API functions of the SearXNG search engine. Through this server, users can directly use SearXNG's web search capabilities in applications that support the MCP protocol (such as Claude Desktop).

How to use the SearXNG MCP Server?

You can use this server in multiple ways: install it as an npm package, run it using a Docker container, or install it with one click via the Smithery tool. After installation, you can use the web search function in MCP - supported client applications.

Use Cases

When you need to: 1. Obtain the latest web information in AI conversations 2. Conduct searches within a specific language or time range 3. Safely browse filtered content 4. Convert web content into readable Markdown format

Main Features

Web SearchSupports multiple search types (general search, news, articles, etc.), and allows specifying language, time range, and content security level
Pagination ControlAllows specifying which page of search results to obtain, facilitating the browsing of a large number of results
Time FilterFilters search results by day, month, or year to obtain content within a specific time period
Web Content RetrievalConverts the web content of a specified URL into Markdown format for easy reading and processing

Advantages and Limitations

Advantages
Privacy protection: SearXNG searches do not record user activities
Flexible configuration: Search parameters (language, time range, etc.) can be customized
Multi - platform support: Can be deployed in multiple ways such as npm and Docker
Open - source and free: Based on the MIT license, it can be freely used and modified
Limitations
Depends on the availability and performance of external SearXNG instances
The quality of search results depends on the configured search engines
Requires basic server deployment knowledge

How to Use

Choose an Installation Method
Choose the most suitable installation method according to your environment: npm, Docker, or one - click installation with Smithery
Configure the SearXNG Instance
Set the SEARXNG_URL environment variable to point to the SearXNG instance you choose (you can use a public instance or build your own)
Integrate into the MCP Client
Add the server configuration to the client configuration file (such as claude_desktop_config.json for Claude Desktop)
Start Using
You can use the search function in the client application, for example: /search query term

Usage Examples

Search for the Latest Technology NewsGet the latest news about artificial intelligence in the past month
Read a Technical ArticleGet the Markdown content of a specific technical article
Multilingual SearchSearch for safely filtered French - language content

Frequently Asked Questions

How to choose a suitable SearXNG instance?
What are the differences between safe search levels?
Why are my search results few?
Can I use multiple SearXNG instances simultaneously?

Related Resources

SearXNG Official Website
Official documentation for the SearXNG search engine
List of Public SearXNG Instances
List of available public SearXNG instances and their status
Introduction to the MCP Protocol
Official introduction to the Model Context Protocol
GitHub Repository
Source code repository for the project
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "searxng": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-searxng"
      ],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
      }
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "command": "mcp-searxng",
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
      }
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SEARXNG_URL",
        "isokoliuk/mcp-searxng:latest"
      ],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
      }
    }
  }
}

{
  "mcpServers": {
    "searxng": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SEARXNG_URL",
        "mcp-searxng:latest"
      ],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
677
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
363
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
863
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
247
4 points
C
Cloudflare
Changesets is a build tool for managing versions and releases in multi - package or single - package repositories.
TypeScript
1.5K
5 points
E
Eino
Eino is an LLM application development framework designed specifically for Golang, aiming to simplify the AI application development process through concise, scalable, reliable, and efficient component abstraction and orchestration capabilities. It provides a rich component library, powerful graphical orchestration functions, complete stream processing support, and a highly scalable aspect mechanism, covering the full-cycle toolchain from development to deployment.
Go
3.5K
5 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
1.1K
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
265
4.2 points
Featured MCP Services
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
1.8K
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
122
4.3 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
173
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
863
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
6.7K
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#
593
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
779
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
5.3K
4.7 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase