mcp-searxng

mcp-searxng

3.3

If you are the rightful owner of mcp-searxng and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

An example of an MCP Server for use by an AI Agent, designed to allow the AI Agent to search for new external information through SearXNG's open-source meta-search engine.

The mcp-searxng is a Model Context Protocol (MCP) server that integrates with SearXNG, an open-source meta-search engine, to provide AI agents with the ability to search for external information. This server is particularly useful for businesses that require privacy and security while enabling AI agents to access diverse search results from multiple search engines. By leveraging SearXNG, mcp-searxng combines results from various search engines, overcoming the limitations of individual search engines like Google, DuckDuckGo, and others. The server is built using Python and utilizes SSE (Server-Sent Events) for communication, allowing for a decoupled architecture suitable for cloud-native applications. The server can be self-hosted or run using Docker, providing flexibility in deployment.

Features

  • Integration with SearXNG: Combines results from multiple search engines for comprehensive search capabilities.
  • Privacy and Security: Offers a way to maintain control over data privacy and security.
  • SSE-based Communication: Allows for decoupled server-client architecture, suitable for cloud-native environments.
  • Docker Support: Provides easy deployment and management using Docker.
  • Markdown Conversion: Uses Microsoft's markdownify to convert web pages into Markdown-formatted text.

Tools

  1. web_search

    Used to perform keyword searches

  2. web_url_read

    Used to read the content of the specified URL