akhq
Experimental Model Context Protocol server for Kafka monitoring tool AKHQ
claude mcp add --transport stdio saarw-akhq-mcp-server npx akhq-mcp-server
How to use
This MCP server acts as an integration layer between AKHQ and the MCP ecosystem. It enables AI assistants and MCP clients to connect to AKHQ through a standardized MCP interface, allowing agents to inspect AKHQ data, navigate clusters, topics, consumers, and more from within familiar MCP-enabled tools. Once running, configure your MCP client (for example Cursor or Claude) to point at the akhq server so the agent can send queries, fetch AKHQ state, and run guided actions alongside your normal workflow. The akhq MCP server is designed to be lightweight and experimental, focusing on enabling conversational querying and assisted navigation within AKHQ rather than replacing AKHQ itself.
To use it, add the akhq-mcp-server entry to your MCP configuration (as shown in installation instructions) and start the server. Then, in your MCP-enabled assistant, select the akhq server as a tool when you need to investigate topics, clusters, pipelines, or consumer groups in AKHQ. The integration lets you issue commands or queries that translate to AKHQ API calls, and present results back to you in natural language or structured formats.
How to install
Prerequisites:
- Node.js installed on your machine (version compatible with the akhq-mcp-server package).
- Access to the AKHQ instance you want to integrate (if needed, provide credentials or network access in your environment).
Installation steps:
-
Ensure Node is installed. You can verify with: node -v npm -v
-
Add the MCP server to your MCP clients configuration by using npx and the server identifier as shown:
{ "mcpServers": { "akhq": { "command": "npx", "args": ["akhq-mcp-server"] } } }
-
Start the MCP server via your MCP client or by running directly (depending on how you manage MCP servers in your environment). If using npx directly, you can test readiness by attempting to connect from your MCP client and verifying a successful handshake.
-
In your MCP client, select the akhq server (akhq) as a tool whenever you want to query or interact with AKHQ data through the assistant.
Additional notes
Notes and tips:
- This server is labeled experimental. Expect ongoing changes in capabilities and API surfaces.
- Ensure your AKHQ instance is reachable from the environment where the MCP server runs (network access, firewall rules, and any required authentication).
- If you need to pass credentials or additional headers to AKHQ, consider extending the MCP client configuration or environment as appropriate for your setup.
- If the MCP client cannot resolve the akhq-mcp-server when using npx, confirm that npm is configured to access the registry and that your environment has network access to fetch the package.
- You can modify the MCP config in your client to rename the server entry or add more tools if you plan to extend integration with other services.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.