RTC MCP Server

Name: RTC MCP Server
Author: gnuhpc

@gnuhpc

Repository

About RTC MCP Server

A Model Context Protocol (MCP) server implementation for managing Alibaba Cloud Realtime Computing Flink resources

#rtc-mcp-server #flink #cloud-computing

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "rtc-mcp-server": {
      "command": "java",
      "args": [
        "-Dtransport.mode=stdio",
        "-Dspring.main.web-application-type=none",
        "-Dspring.main.banner-mode=off",
        "-Dlogging.file.name=/path/to/rtc-mcp-server/mcpserver.log",
        "-jar",
        "/path/to/rtc-mcp-server/target/rtc-mcp-server-1.0-SNAPSHOT.jar"
      ],
      "env": {
        "ALIYUN_ACCESS_KEY_ID": "your-access-key-id",
        "ALIYUN_ACCESS_KEY_SECRET": "your-access-key-secret"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Tools

Start a deployed Flink job

Stop a running Flink job

List all jobs in a deployment

Delete a non-running job

Get job diagnosis information

Create a new Flink deployment

Get deployment metrics

Create a savepoint for a job

Create a new variable

Update an existing variable

Delete a variable

List variables with pagination

Create a new workspace

Get workspace information

List all workspaces

Get catalog information

Get database information

Get table information

Execute SQL statements

Overview

What is RTC MCP Server?

The RTC MCP Server is a Model Context Protocol (MCP) server implementation for managing Alibaba Cloud Realtime Compute for Apache Flink resources. It provides a standardized interface for AI models to interact with Alibaba Cloud Flink services.

How to use RTC MCP Server?

Build the project using Maven (mvn clean package) and run the JAR (java -jar target/rtc-mcp-server-1.0-SNAPSHOT.jar). Configure the MCP client with the java command, passing the JAR path and setting Alibaba Cloud credentials in environment variables (ALIYUN_ACCESS_KEY_ID and ALIYUN_ACCESS_KEY_SECRET). Use the available MCP tools to manage Flink resources.

Key features of RTC MCP Server

Create and manage Flink clusters
Create and manage Flink SQL jobs and deployments
Monitor job status and metrics
Create and manage savepoints
Workspace and namespace management
Catalog operations and SQL statement execution
Support for webflux and stdio transport modes

Use cases of RTC MCP Server

Automating Flink cluster and job management via AI assistants
Integrating Alibaba Cloud Flink operations with MCP-compatible tools
Performing ad-hoc SQL queries and catalog lookups on Flink deployments
Managing deployment lifecycles, including savepoints and metrics retrieval

FAQ from RTC MCP Server

What prerequisites are needed to run the RTC MCP Server?

JDK 17 or higher, Maven 3.6 or higher, an Alibaba Cloud account with Realtime Compute access, and an Access Key ID and Secret.

How do I configure Alibaba Cloud credentials?

Set the ALIYUN_ACCESS_KEY_ID and ALIYUN_ACCESS_KEY_SECRET environment variables in the MCP client configuration (e.g., cline_mcp_settings.json).

What MCP tools does the server provide?

The server provides tools for job management (start, stop, list, delete, diagnose), deployment management (create, get metrics, create savepoint), variable management (CRUD), workspace management (create, get info, list), and catalog operations (get catalogs, databases, tables, execute SQL).