Use This MCP server To

Integrate real-time web search results into AI model responses Provide up-to-date information from Google, Bing, and Quark search engines Enhance chatbot answers with current internet data Support AI-driven research with live search capabilities Enable dynamic content generation based on latest web information Combine AI reasoning with external search data for accuracy Improve customer support bots with real-time knowledge retrieval

README

MseeP.ai Security Assessment Badge

Higress AI-Search MCP Server

Overview

A Model Context Protocol (MCP) server that provides an AI search tool to enhance AI model responses with real-time search results from various search engines through Higress ai-search feature.

Demo

Cline

cline-higress-ai-search.mp4

Claude Desktop

higress-ai-search-demo.mp4

Features

Internet Search: Google, Bing, Quark - for general web information
Academic Search: Arxiv - for scientific papers and research
Internal Knowledge Search

Prerequisites

uv for package installation.
Config Higress with ai-search plugin and ai-proxy plugin.

Configuration

The server can be configured using environment variables:

HIGRESS_URL(optional): URL for the Higress service (default: http://localhost:8080/v1/chat/completions).
MODEL(required): LLM model to use for generating responses.
INTERNAL_KNOWLEDGE_BASES(optional): Description of internal knowledge bases.

Option 1: Using uvx

Using uvx will automatically install the package from PyPI, no need to clone the repository locally.

{
  "mcpServers": {
    "higress-ai-search-mcp-server": {
      "command": "uvx",
      "args": [
        "higress-ai-search-mcp-server"
      ],
      "env": {
        "HIGRESS_URL": "http://localhost:8080/v1/chat/completions",
        "MODEL": "qwen-turbo",
        "INTERNAL_KNOWLEDGE_BASES": "Employee handbook, company policies, internal process documents"
      }
    }
  }
}

Option 2: Using uv with local development

Using uv requires cloning the repository locally and specifying the path to the source code.

{
  "mcpServers": {
    "higress-ai-search-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/src/higress-ai-search-mcp-server",
        "run",
        "higress-ai-search-mcp-server"
      ],
      "env": {
        "HIGRESS_URL": "http://localhost:8080/v1/chat/completions",
        "MODEL": "qwen-turbo",
        "INTERNAL_KNOWLEDGE_BASES": "Employee handbook, company policies, internal process documents"
      }
    }
  }
}

License

This project is licensed under the MIT License - see the LICENSE file for details.

higress-ai-search-mcp-server FAQ

How does the Higress AI-Search MCP Server fetch search results?

It uses the Higress ai-search plugin to query multiple search engines like Google, Bing, and Quark in real time.

Can this MCP server be used with any LLM provider?

Yes, it is provider-agnostic and works with OpenAI, Claude, Gemini, and others.

Is internet access required for the Higress AI-Search MCP Server?

Yes, it requires internet connectivity to perform live searches on external search engines.

How does this server improve AI model responses?

By providing up-to-date search results, it enriches AI answers with current and relevant information beyond its training data.

What search engines are supported by this MCP server?

It supports Google, Bing, and Quark search engines for diverse and comprehensive results.

Is the Higress AI-Search MCP Server secure to use?

Yes, it follows MCP principles for secure, scoped, and observable interactions with external data sources.

Can I customize which search engines to query?

Configuration options depend on the Higress ai-search plugin setup, allowing flexibility in search engine selection.

Does it support multi-language search queries?

Support depends on the underlying search engines; Google, Bing, and Quark generally support multiple languages.