Skip to main content
Glama
CLAUDE_SETUP.md3.66 kB
# KafkaIQ + Claude Desktop Setup Guide ## Step 1: Locate Claude Desktop Config File The Claude Desktop configuration file is located at: ``` C:\Users\ayush\AppData\Roaming\Claude\claude_desktop_config.json ``` ## Step 2: Update the Configuration 1. **Close Claude Desktop** if it's running 2. **Open the config file** in a text editor (Notepad, VS Code, etc.) 3. **Replace the contents** with: ```json { "mcpServers": { "kafkaiq": { "command": "python", "args": [ "c:\\Users\\ayush\\KafkaIQ\\mcp_server.py" ], "env": {}, "transport": "stdio" } } } ``` **OR** if the file already has content, add the `kafkaiq` server to the existing `mcpServers` object. ## Step 3: Restart Claude Desktop 1. Close Claude Desktop completely 2. Reopen Claude Desktop 3. Look for a 🔌 (plug) icon or MCP indicator showing KafkaIQ is connected ## Step 4: Test the Integration In Claude Desktop, try these commands: ### Connect to Kafka ``` Connect to my Kafka cluster at localhost:9092 ``` ### List Topics ``` Show me all the topics in my Kafka cluster ``` ### Check Consumer Lag ``` What's the consumer lag for the orders-processor group on the orders topic? ``` ### Get Cluster Health ``` Give me a health summary of my Kafka cluster ``` ### Create a Topic ``` Create a new topic called 'test-topic' with 3 partitions ``` ## Troubleshooting ### If KafkaIQ doesn't appear in Claude Desktop: 1. **Check the config file path** - Make sure it's exactly: `C:\Users\ayush\AppData\Roaming\Claude\claude_desktop_config.json` 2. **Verify Python path** - Open Command Prompt and run: ```cmd python --version ``` Make sure Python is accessible 3. **Check MCP server file** - Verify the file exists: ```cmd dir c:\Users\ayush\KafkaIQ\mcp_server.py ``` 4. **View Claude Desktop logs**: - Windows: `%APPDATA%\Claude\logs\` - Look for any error messages ### If commands don't work: 1. **Ensure Kafka is running**: ```cmd docker ps ``` You should see `docker-kafka-1` and `docker-zookeeper-1` 2. **Test MCP server manually**: ```cmd cd c:\Users\ayush\KafkaIQ python mcp_server.py ``` ## What You Can Do with KafkaIQ Once connected, you can use natural language to: ✅ **Manage Topics** - List, create, delete, describe topics - Get topic configurations - Check partition details ✅ **Monitor Consumers** - Check consumer lag - View consumer groups - Analyze partition assignments ✅ **Cluster Health** - Get cluster details - Check broker status - View partition leadership - Get intelligent health summaries ✅ **Troubleshooting** - Find offline partitions - Check under-replicated partitions - Monitor broker resources ## Example Workflow ``` You: "Connect to localhost:9092" Claude: ✓ Connected to Kafka cluster You: "What topics do I have?" Claude: You have 6 topics: events, my-topic, notifications, orders, payments, users You: "Show me consumer lag for orders-processor" Claude: The orders-processor group has a lag of 15,234 messages on the orders topic You: "Is my cluster healthy?" Claude: Your cluster is healthy! 1 broker running, 6 topics, no offline partitions ``` ## Quick Reference **Config File Location:** ``` C:\Users\ayush\AppData\Roaming\Claude\claude_desktop_config.json ``` **Alternative: Copy the pre-made config** I've created a config file at: ``` c:\Users\ayush\KafkaIQ\claude_desktop_config.json ``` You can copy this to the Claude Desktop config location. --- **Need Help?** - Check Claude Desktop documentation: https://docs.anthropic.com/claude/docs/mcp - View KafkaIQ README: `c:\Users\ayush\KafkaIQ\Readme.md`

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ojhaayush03/kafka_mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server