apache-flink-mcp-server — Claude Code MCP server
MCP server for Claude Code and other clients that connects AI assistants to Apache Flink clusters.
MIT ★ 13 updated 2026-11-15
Open on GitHubWhat apache-flink-mcp-server does
The server enables conversational management of stream processing applications. It provides tools for cluster monitoring, metric collection, and exception tracking. Prerequisites include a running Apache Flink cluster and Python 3.8 or higher.
Multiple Flink clusters can be registered simultaneously by passing specific connection identifiers. The available toolset covers TaskManager resource inspection, uploaded JAR file listing, and email notifications.
What it helps with
- monitor Apache Flink cluster health
- inspect streaming job performance metrics
- retrieve exception logs for debugging
- check TaskManager resource utilization
Example prompts for the agent
- What is the status of my Flink cluster?
- Can you help me debug job abc123?
How to install apache-flink-mcp-server
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about apache-flink-mcp-server
What does apache-flink-mcp-server do?
It connects AI assistants to Apache Flink clusters for natural language monitoring, management, and debugging.
What is required to run apache-flink-mcp-server?
You need an accessible Apache Flink cluster, Python 3.8 or higher, and an MCP-compatible client.
How to configure apache-flink-mcp-server in Continue?
Add the server entry with type streamable-http and URL http://127.0.0.1:9090/mcp/ to your Continue configuration file.