Higress AI Search MCP server

The Higress AI-Search MCP Server is a powerful tool that enhances AI model responses by providing real-time search results from various search engines through the Higress ai-search feature. It acts as a Model Context Protocol (MCP) server to augment AI capabilities with up-to-date information.

Features

• Internet Search: Access Google, Bing, and Quark search engines for general web information
• Academic Search: Query Arxiv for scientific papers and research articles
• Internal Knowledge Search: Retrieve information from company knowledge bases

Prerequisites

Before setting up the Higress AI-Search MCP Server, you'll need:

• uv installed for package management
• Higress configured with the ai-search plugin and ai-proxy plugin

Configuration Options

You can configure the server through environment variables:

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

Installation Methods

Using uvx (Recommended)

This method installs the package directly from PyPI without requiring you 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"
      }
    }
  }
}

Using uv with Local Development

If you need to use a local development version:

1. Clone the repository
2. Configure the server with the path to your local 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"
      }
    }
  }
}

Usage

Once configured, the Higress AI-Search MCP Server will automatically enhance your AI model's capabilities by providing:

• Real-time web search results from multiple search engines
• Academic paper information from Arxiv
• Internal knowledge from your company's specified knowledge bases

The server integrates seamlessly with compatible AI interfaces like Claude Desktop and other MCP-enabled clients to provide enriched responses with the latest information available.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.