Manage Higress gateway configuration and operations through MCP tools, with a LangGraph-based client for stdio workflows.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
One-click editor setup isn’t available for this listing yet — we don’t have a confirmed install command, and we’d rather show nothing than point your editor at the wrong package or host. Follow the project’s own setup instructions, linked above.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Higress Ops MCP Server.
higress-group/higress-ops-mcp-server provides an MCP interface for configuring and managing Higress. Its tools are backed by a Higress client that communicates with the Higress Console API using HTTP requests. The repository also includes a client application that connects the MCP workflow to LangGraph and LangChain MCP Adapters.
The example tool registration structure covers common operations, request-block handling, routes, and service sources. The README also shows write operations such as adding or updating routes, service sources, and request-block plugins as sensitive actions that can require human confirmation.
The project uses a Python MCP server architecture. Tool classes expose functions through FastMCP, while the Higress client encapsulates calls to Console API endpoints. New API-backed operations are added by implementing a client method, wrapping it in an MCP tool, and registering the tool class in the server’s tool list.
In stdio mode, the client process starts the MCP server. The documented startup command is uv run client.py, which launches both parts of the local workflow. This arrangement is intended for an MCP client or agent flow that can invoke the registered Higress operations.
Configuration is supplied through environment variables. The repository instructs users to copy .env.example to .env and populate the required values, but the provided material does not list the variable names or their expected values.
To run the included client and server flow, use:
The command is for the repository’s Python application and is not a hosted endpoint configuration. The available documentation specifically describes stdio operation.
The higress-group/higress-ops-mcp-server structure supports:
The repository is also designed for extension. A new tool can be placed in a new category or added to an existing class, then registered with the server. API methods are kept in the Higress client rather than implemented directly in each tool.
The supplied README excerpt does not provide a complete inventory of exposed tools, a list of required environment variable names, authentication details, or a published license. It also documents the combined client-and-server startup flow rather than a separate standalone server command. Confirm the current repository configuration before deploying it in a different MCP client or transport mode.
Sensitive-tool confirmation is represented in the project configuration. This indicates that some changes may require human approval, but the excerpt does not describe the confirmation mechanism or how approval is presented to users.
Always refer to the official documentation for the most accurate and up-to-date information on how to configure and run this server.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/higress-group-higress-ops-mcp-server)<a href="https://allmcps.com/mcp/higress-group-higress-ops-mcp-server"><img src="https://allmcps.com/api/badge/higress-group-higress-ops-mcp-server?style=directory" alt="Higress Ops MCP Server on AllMCPs" /></a>