mcp-searxng

mcp-searxng

An MCP server that integrates the SearXNG API for web search and URL content extraction with advanced features like pagination, caching, and proxy support.

Category
访问服务器

README

SearXNG MCP Server

An MCP server implementation that integrates the SearXNG API, providing web search capabilities.

https://nodei.co/npm/mcp-searxng.png?downloads=true&downloadRank=true&stars=true

https://badgen.net/docker/pulls/isokoliuk/mcp-searxng

<a href="https://glama.ai/mcp/servers/0j7jjyt7m9"><img width="380" height="200" src="https://glama.ai/mcp/servers/0j7jjyt7m9/badge" alt="SearXNG Server MCP server" /></a>

Features

  • Web Search: General queries, news, articles, with pagination.
  • URL Content Reading: Advanced content extraction with pagination, section filtering, and heading extraction.
  • Intelligent Caching: URL content is cached with TTL (Time-To-Live) to improve performance and reduce redundant requests.
  • Pagination: Control which page of results to retrieve.
  • Time Filtering: Filter results by time range (day, month, year).
  • Language Selection: Filter results by preferred language.
  • Safe Search: Control content filtering level for search results.

Tools

  • searxng_web_search

    • Execute web searches with pagination
    • Inputs:
      • query (string): The search query. This string is passed to external search services.
      • pageno (number, optional): Search page number, starts at 1 (default 1)
      • time_range (string, optional): Filter results by time range - one of: "day", "month", "year" (default: none)
      • language (string, optional): Language code for results (e.g., "en", "fr", "de") or "all" (default: "all")
      • safesearch (number, optional): Safe search filter level (0: None, 1: Moderate, 2: Strict) (default: instance setting)
  • web_url_read

    • Read and convert the content from a URL to markdown with advanced content extraction options
    • Inputs:
      • url (string): The URL to fetch and process
      • startChar (number, optional): Starting character position for content extraction (default: 0)
      • maxLength (number, optional): Maximum number of characters to return
      • section (string, optional): Extract content under a specific heading (searches for heading text)
      • paragraphRange (string, optional): Return specific paragraph ranges (e.g., '1-5', '3', '10-')
      • readHeadings (boolean, optional): Return only a list of headings instead of full content

Configuration

Environment Variables

Required

  • SEARXNG_URL: SearXNG instance URL (default: http://localhost:8080)
    • Format: <protocol>://<hostname>[:<port>]
    • Example: https://search.example.com

Optional

  • AUTH_USERNAME / AUTH_PASSWORD: HTTP Basic Auth credentials for searxng_web_search (password-protected SearXNG instances)
  • USER_AGENT: Global default User-Agent header used by both searxng_web_search and web_url_read (e.g., MyBot/1.0)
  • URL_READER_USER_AGENT: Custom User-Agent specifically for the web_url_read tool (overrides USER_AGENT for URL reading requests)
  • HTTP_PROXY / HTTPS_PROXY: Global proxy URLs for routing traffic (fallback for both interfaces)
    • Format: http://[username:password@]proxy.host:port
  • NO_PROXY: Comma-separated bypass list (e.g., localhost,.internal,example.com)
Interface-Specific Proxies (Optional)
  • SEARCH_HTTP_PROXY / SEARCH_HTTPS_PROXY: Proxy for searxng_web_search tool only
  • URL_READER_HTTP_PROXY / URL_READER_HTTPS_PROXY: Proxy for web_url_read tool only
    • These take priority over HTTP_PROXY/HTTPS_PROXY for their respective interfaces

Advanced Configuration

# Separate proxies for search and URL reading
SEARCH_HTTP_PROXY=http://search-proxy:8080
URL_READER_HTTP_PROXY=http://reader-proxy:8080

# Custom user_agent for URL reader
URL_READER_USER_AGENT="Mozilla/5.0 (compatible; Bot/1.0)"

Installation & Configuration

NPX

{
  "mcpServers": {
    "searxng": {
      "command": "npx",
      "args": ["-y", "mcp-searxng"],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL"
      }
    }
  }
}

<details> <summary>Full Configuration Example (All Options)</summary>

{
  "mcpServers": {
    "searxng": {
      "command": "npx",
      "args": ["-y", "mcp-searxng"],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
        "AUTH_USERNAME": "your_username",
        "AUTH_PASSWORD": "your_password",
        "USER_AGENT": "MyBot/1.0",
        "URL_READER_USER_AGENT": "Mozilla/5.0 (compatible; MyBot/1.0)",
        "SEARCH_HTTP_PROXY": "http://search-proxy.company.com:8080",
        "URL_READER_HTTP_PROXY": "http://reader-proxy.company.com:8080",
        "HTTP_PROXY": "http://global-proxy.company.com:8080",
        "HTTPS_PROXY": "http://global-proxy.company.com:8080",
        "NO_PROXY": "localhost,127.0.0.1,.local,.internal"
      }
    }
  }
}

Note: Mix and match environment variables as needed. All optional variables can be used independently or together.

</details>

NPM

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

<details> <summary>Full Configuration Example (All Options)</summary>

{
  "mcpServers": {
    "searxng": {
      "command": "mcp-searxng",
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
        "AUTH_USERNAME": "your_username",
        "AUTH_PASSWORD": "your_password",
        "USER_AGENT": "MyBot/1.0",
        "URL_READER_USER_AGENT": "Mozilla/5.0 (compatible; MyBot/1.0)",
        "SEARCH_HTTP_PROXY": "http://search-proxy.company.com:8080",
        "URL_READER_HTTP_PROXY": "http://reader-proxy.company.com:8080",
        "HTTP_PROXY": "http://global-proxy.company.com:8080",
        "HTTPS_PROXY": "http://global-proxy.company.com:8080",
        "NO_PROXY": "localhost,127.0.0.1,.local,.internal"
      }
    }
  }
}

</details>

Docker

Using Pre-built Image from Docker Hub

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

<details> <summary>Full Configuration Example (All Options)</summary>

{
  "mcpServers": {
    "searxng": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "SEARXNG_URL",
        "-e", "AUTH_USERNAME",
        "-e", "AUTH_PASSWORD",
        "-e", "USER_AGENT",
        "-e", "URL_READER_USER_AGENT",
        "-e", "SEARCH_HTTP_PROXY",
        "-e", "SEARCH_HTTPS_PROXY",
        "-e", "URL_READER_HTTP_PROXY",
        "-e", "URL_READER_HTTPS_PROXY",
        "-e", "HTTP_PROXY",
        "-e", "HTTPS_PROXY",
        "-e", "NO_PROXY",
        "isokoliuk/mcp-searxng:latest"
      ],
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
        "AUTH_USERNAME": "your_username",
        "AUTH_PASSWORD": "your_password",
        "USER_AGENT": "MyBot/1.0",
        "URL_READER_USER_AGENT": "Mozilla/5.0 (compatible; MyBot/1.0)",
        "SEARCH_HTTP_PROXY": "http://search-proxy.company.com:8080",
        "URL_READER_HTTP_PROXY": "http://reader-proxy.company.com:8080",
        "HTTP_PROXY": "http://global-proxy.company.com:8080",
        "HTTPS_PROXY": "http://global-proxy.company.com:8080",
        "NO_PROXY": "localhost,127.0.0.1,.local,.internal"
      }
    }
  }
}

Note: Add only the -e flags and env variables you need.

</details>

Build Locally

docker build -t mcp-searxng:latest -f Dockerfile .

Use the same configuration as above, replacing isokoliuk/mcp-searxng:latest with mcp-searxng:latest.

Docker Compose

Create a docker-compose.yml file:

services:
  mcp-searxng:
    image: isokoliuk/mcp-searxng:latest
    stdin_open: true
    environment:
      - SEARXNG_URL=YOUR_SEARXNG_INSTANCE_URL
      # Add any optional variables as needed:
      # - AUTH_USERNAME=your_username
      # - AUTH_PASSWORD=your_password
      # - USER_AGENT=MyBot/1.0
      # - URL_READER_USER_AGENT=Mozilla/5.0 (compatible; MyBot/1.0)
      # - SEARCH_HTTP_PROXY=http://search-proxy.company.com:8080
      # - URL_READER_HTTP_PROXY=http://reader-proxy.company.com:8080
      # - HTTP_PROXY=http://global-proxy.company.com:8080
      # - HTTPS_PROXY=http://proxy.company.com:8080
      # - NO_PROXY=localhost,127.0.0.1,.local,.internal

Then configure your MCP client:

{
  "mcpServers": {
    "searxng": {
      "command": "docker-compose",
      "args": ["run", "--rm", "mcp-searxng"]
    }
  }
}

HTTP Transport (Optional)

The server supports both STDIO (default) and HTTP transports. Set MCP_HTTP_PORT to enable HTTP mode.

{
  "mcpServers": {
    "searxng-http": {
      "command": "mcp-searxng",
      "env": {
        "SEARXNG_URL": "YOUR_SEARXNG_INSTANCE_URL",
        "MCP_HTTP_PORT": "3000"
      }
    }
  }
}

HTTP Endpoints:

  • MCP Protocol: POST/GET/DELETE /mcp
  • Health Check: GET /health

Testing:

MCP_HTTP_PORT=3000 SEARXNG_URL=http://localhost:8080 mcp-searxng
curl http://localhost:3000/health

Troubleshooting

403 Forbidden Error from SearXNG

If you receive a 403 Forbidden error when using mcp-searxng, it is likely because your SearXNG instance does not have JSON format enabled. This server requests results in JSON format (format=json), which must be explicitly allowed in SearXNG's configuration.

To fix this, edit your SearXNG settings.yml (commonly located at /etc/searxng/settings.yml) and add json to the list of allowed formats:

search:
  formats:
    - html
    - json

After saving the file, restart your SearXNG instance. For example, if running with Docker:

docker restart searxng

You can verify JSON format is working by running:

curl 'http://localhost:8080/search?q=test&format=json'

You should receive a JSON response. If you still get a 403 error, double-check that:

  • The settings.yml file is correctly mounted into your Docker container
  • The YAML indentation is correct
  • The SearXNG instance was fully restarted after the configuration change

For more details, see the SearXNG settings documentation and this discussion.

Running evals

SEARXNG_URL=YOUR_URL OPENAI_API_KEY=your-key npx mcp-eval evals.ts src/index.ts

For Developers

Contributing

We welcome contributions! Follow these guidelines:

Coding Standards:

  • Use TypeScript with strict type safety
  • Follow existing error handling patterns
  • Write concise, informative error messages
  • Include unit tests for new functionality
  • Maintain 90%+ test coverage
  • Test with MCP inspector before submitting
  • Run evals to verify functionality

Workflow:

  1. Fork and clone:

    git clone https://github.com/YOUR_USERNAME/mcp-searxng.git
    cd mcp-searxng
    git remote add upstream https://github.com/ihor-sokoliuk/mcp-searxng.git
    
  2. Setup:

    npm install
    npm run watch  # Development mode with file watching
    
  3. Development:

    git checkout -b feature/your-feature-name
    # Make changes in src/
    npm run build
    npm test
    npm run test:coverage
    npm run inspector
    
  4. Submit:

    git commit -m "feat: description"
    git push origin feature/your-feature-name
    # Create PR on GitHub
    

Testing

npm test                    # Run all tests
npm run test:coverage      # Generate coverage report
npm run test:watch         # Watch mode

Coverage: 100% success rate with comprehensive unit tests covering error handling, types, proxy configs, resources, and logging.

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选