Higress Ops MCP Server

🚀 Higress OPS MCP Server

A server implementing the Model Context Protocol (MCP) for comprehensive configuration and management of Higress. This repository also provides an MCP client built on LangGraph and LangChain MCP adapters, which interacts with the Higress MCP server through a well-designed proxy process architecture.

🚀 Quick Start

✨ Features

• Implements the Model Context Protocol (MCP) for Higress configuration and management.
• Provides an MCP client built on LangGraph and LangChain MCP adapters.
• Enables interaction with the Higress MCP server through a well - designed proxy process architecture.

📦 Installation

Configure Environment Variables

Copy the .env.example file to .env and fill in the corresponding values.

Start the MCP Client and MCP Server

In the standard input - output mode, the MCP server process is started by the MCP client program. Run the following command to start the MCP client and MCP server:

uv run client.py

💻 Usage Examples

Basic Usage

The basic usage is to start the MCP client and server as described in the installation section.

Advanced Usage - Adding New Tools

Step 1: Create a new tool class or extend an existing class

• Create a new file in the tools directory (if adding a brand - new tool category).
• Or add your tool to an existing class if it fits the existing category.

from typing import Dict, List, Any
from fastmcp import FastMCP

class YourTools:
    def register_tools(self, mcp: FastMCP):
        @mcp.tool()
        async def your_tool_function(arg1: str, arg2: int) -> List[Dict]:
            """
            Your tool description.
            
            Args:
                arg1: Description of arg1
                arg2: Description of arg2

            Returns:
                Description of the return value
            
            Raises:
                ValueError: If the request fails
            """
            # Use self.higress_client to implement API calls
            return self.higress_client.your_api_method(arg1, arg2)

Step 2: If your tool needs to interact with the Higress Console API, add a new method to HigressClient

• Add the method to utils/higress_client.py to encapsulate API calls.
• Use the existing HTTP methods (get, put, post) for actual API communication.

def your_api_method(self, arg1: str, arg2: int) -> List[Dict]:
    """
    Function description of this API method.
    
    Args:
        arg1: Description of arg1
        arg2: Description of arg2
        
    Returns:
        Response data
        
    Raises:
        ValueError: If the request fails
    """
    path = "/v1/your/api/endpoint"
    data = {"arg1": arg1, "arg2": arg2}
    return self.put(path, data)  # Or self.get(path) or self.post(path, data)

Step 3: Register your tool class in the server

• Add your tool class to the tool_classes list in server.py.
• This list is used by ToolsRegister to instantiate and register all tools.
• ToolsRegister will automatically set the logger and higress_client attributes.

tool_classes = [
    CommonTools,
    RequestBlockTools,
    RouteTools,
    ServiceSourceTools,
    YourTools  # Add your tool class here
]

Step 4: If your tool requires human confirmation, add it to SENSITIVE_TOOLS

• Tools in this list require human confirmation before execution.

# Define write operations that require human confirmation
SENSITIVE_TOOLS = [
    "add_route", 
    "add_service_source",
    "update_route",
    "update_request_block_plugin", 
    "update_service_source",
    "your_tool_function"  # Add your tool function here
]

📚 Documentation

Demo

https://github.com/user-attachments/assets/bae66b77-a158-452e-9196-98060bac0df7