higress-ops-mcp-server

Higress OPS MCP Server is a Model Context Protocol (MCP) server implementation designed to provide comprehensive configuration and management capabilities for Higress. This repository also includes an MCP client built on LangGraph and LangChain MCP Adapters, which interacts with the Higress MCP Server through an agent workflow architecture.

Main Capabilities

• Provides an MCP server that supports configuration and management of Higress.
• Provides an MCP client, based on LangGraph and LangChain MCP Adapters, that interacts with the server through an agent workflow.

Usage

1. Configure environment variables: copy the .env.example file to .env and fill in the corresponding values.
2. Start the MCP client and MCP server: in stdio mode, the MCP server process is started by the MCP client program. Run the corresponding command to start the client and server.

Extending Tools

• Step 1: Create a new tool class or extend an existing tool class. If adding an entirely new tool category, create a new file in the tools directory; if it fits an existing category, add the tool to the existing class.
• Step 2: If the tool needs to interact with the Higress Console API, add a new method in HigressClient. Add a method in utils/higress_client.py that wraps the API call, using the existing HTTP methods (get, put, post) for the actual API communication.
• Step 3: Register the tool class in the server. Add the tool class to the tool_classes list in server.py. This list is used by ToolsRegister to instantiate and register all tools. ToolsRegister automatically sets the logger and higress_client attributes.
• Step 4: If the tool requires human confirmation, add it to SENSITIVE_TOOLS. Tools in this list require human confirmation before execution.

Applicable Scenarios

Suitable for scenarios that require configuration and management of the Higress gateway, as well as for developers who wish to interact with Higress through the MCP protocol.## Limitations No information is currently provided regarding fees, pricing, platform support, effectiveness, etc.