mcp-searxng-public MCP Server

What does “mcp-searxng-public” MCP Server do?

The mcp-searxng-public MCP Server acts as a bridge between AI assistants and public SearXNG metasearch instances. Instead of relying on the JSON output—which most public SearXNG servers do not provide—this server fetches HTML search results from up to three public SearXNG instances and parses them into a clean JSON format. This enables AI clients to perform real-time web searches, aggregate data from multiple sources, and retrieve concise summaries of web content in a standardized way. It is valuable for tasks that require up-to-date information retrieval, research, or general-purpose web search within development workflows, all while benefiting from the privacy features of SearXNG.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No resources are explicitly described in the repository.

List of Tools

• search
  The main (and only) tool provided by the server. It allows LLMs to perform web searches using public SearXNG instances. The tool takes a query (the search string) and an optional time_range (e.g., “day”, “month”, “year”), and returns an array of JSON objects with url and summary fields for each result.

Use Cases of this MCP Server

• Real-time Web Search
  Enables AI assistants to fetch up-to-date information from the web for answering questions, research, and summarization tasks.
• Aggregated Data Retrieval
  Pulls results from multiple SearXNG instances, increasing robustness and coverage of search results for developers and users.
• Summary Extraction
  Automatically parses and summarizes web content into JSON, facilitating downstream processing and integration into other tools or workflows.
• Privacy-Respecting Information Gathering
  Leverages SearXNG’s privacy-respecting architecture, avoiding user profiling or tracking during information retrieval.
• Fallback Search Mechanisms
  Supports multiple SearXNG instances for improved reliability and resilience against downtime or rate limits.

How to set it up

Windsurf

1. Prerequisites: Ensure Node.js and npm are installed.
2. Install the server:
   npm install mcp-searxng-public
3. Edit configuration: Locate your Windsurf MCP configuration file.
4. Add MCP server configuration: Insert the following JSON snippet:

   {
     "name": "SearXNGScraper",
     "type": "stdio",
     "command": "npx",
     "args": ["mcp-searxng-public"],
     "capabilities": {
       "tool-calls": true
     },
     "env": {
       "SEARXNG_BASE_URL": "https://searx.be;https://searx.tiekoetter.com;https://opnxng.com;https://searxng.world;https://searx.oloke.xyz;https://seek.fyi"
     }
   }
   

5. Save and restart Windsurf, then verify the server is available.

Claude

1. Prerequisites: Install Node.js and npm.
2. Install the server:
   npm install mcp-searxng-public
3. Edit Claude’s configuration file for MCP servers.
4. Add MCP server configuration:

   {
     "name": "SearXNGScraper",
     "type": "stdio",
     "command": "npx",
     "args": ["mcp-searxng-public"],
     "capabilities": {
       "tool-calls": true
     },
     "env": {
       "SEARXNG_BASE_URL": "https://searx.be;https://searx.tiekoetter.com;https://opnxng.com;https://searxng.world;https://searx.oloke.xyz;https://seek.fyi"
     }
   }
   

5. Save and restart Claude to apply changes.

Cursor

1. Ensure Node.js and npm are available.
2. Install the package:
   npm install mcp-searxng-public
3. Open Cursor’s MCP server configuration.
4. Add the server using:

   {
     "name": "SearXNGScraper",
     "type": "stdio",
     "command": "npx",
     "args": ["mcp-searxng-public"],
     "capabilities": {
       "tool-calls": true
     },
     "env": {
       "SEARXNG_BASE_URL": "https://searx.be;https://searx.tiekoetter.com;https://opnxng.com;https://searxng.world;https://searx.oloke.xyz;https://seek.fyi"
     }
   }
   

5. Restart Cursor and ensure the MCP server is detected.

Cline

1. Install Node.js and npm if not already installed.
2. Install the server:
   npm install mcp-searxng-public
3. Edit Cline’s MCP configuration.
4. Insert the server configuration:

   {
     "name": "SearXNGScraper",
     "type": "stdio",
     "command": "npx",
     "args": ["mcp-searxng-public"],
     "capabilities": {
       "tool-calls": true
     },
     "env": {
       "SEARXNG_BASE_URL": "https://searx.be;https://searx.tiekoetter.com;https://opnxng.com;https://searxng.world;https://searx.oloke.xyz;https://seek.fyi"
     }
   }
   

5. Save the file and restart Cline for the changes to take effect.

Securing API Keys

• For public SearXNG, API keys are not required, but if using private instances that require authentication, set secrets in the env section:

  "env": {
    "SEARXNG_BASE_URL": "...",
    "SEARXNG_API_KEY": "${SEARXNG_API_KEY}"
  },
  "inputs": {
    "SEARXNG_API_KEY": {
      "type": "string",
      "secret": true
    }
  }
  

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "mcp-searxng-public": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “mcp-searxng-public” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The mcp-searxng-public MCP Server is simple and focused, providing a single, robust web search tool for AI assistants. Its lack of prompt templates and explicit resource exposure limits flexibility, but its functionality is valuable for privacy-centric, real-time information retrieval. The setup is straightforward, and the documentation is clear. However, advanced MCP features like Roots and Sampling support are missing or not documented.

Overall, I’d rate this MCP server a 5/10: solid for its purpose, but basic in terms of protocol features and extensibility.

MCP Score