Apache Pinot + Klavis AI: Complete MCP Integration
Apache Pinot is a MCP server that MCP server for Apache Pinot real-time analytics database with SQL query capabilities and metadata access.
When integrated with Klavis AI, you can:
- List and inspect Apache Pinot tables
- View and analyze table segments
- Retrieve and analyze table schemas
This guide provides step-by-step instructions to set up Apache Pinot in Klavis AI, including configuration, examples, and troubleshooting.
What You'll Achieve
After completing this setup:
- Apache Pinot will be fully integrated and operational
- You can use Apache Pinot tools directly in Klavis AI
- All Apache Pinot capabilities will be available for your workflows
- Access to 5 different tools
Prerequisites
Before starting, ensure you have:
- Apache Pinot broker hostname
- Apache Pinot broker port
- Klavis AI installed and configured
- Compatible operating system (Cloud (klavis.ai), Self-Hosted (Docker), Python SDK, TypeScript SDK)
Installation
Step 1: Install Apache Pinot
Configuration
Step 2: Configure Klavis AI
- Open Klavis AI settings
- Navigate to MCP server configuration
- Add Apache Pinot server with appropriate settings
- Save and restart if needed
Examples
Once configured, you can use Apache Pinot in Klavis AI:
List All Tables
Get overview of available Pinot tables
Ask Klavis AI: "Show me all the tables available in the Pinot cluster"
Expected Result: List of table names with basic metadata and schema information
Execute Analytics Query
Run SQL query for real-time analytics
Ask Klavis AI: "SELECT COUNT(*) FROM events WHERE timestamp > now() - 3600000"
Expected Result: Query results showing event count for last hour
Analyze Table Structure
Get detailed schema information for a table
Ask Klavis AI: "Show me the schema and structure of the user_events table"
Expected Result: Table schema with column names, types, and index information
Generate Data Visualization
Create histogram plots from query results
Ask Klavis AI: "Create a histogram showing user activity distribution by hour"
Expected Result: Histogram visualization with data aggregated by time buckets
Testing Your Setup
- Launch Klavis AI
- Verify Apache Pinot is available in the tools list
- Test basic Apache Pinot functionality
Troubleshooting
Common Issues
uv Command Not Found
Symptoms: Command not found error, uv: command not found
Cause: uv package manager not installed
Solution:
- Install uv using: curl -LsSf https://astral.sh/uv/install.sh | sh
- Restart terminal or source shell configuration
- Verify installation with: uv --version
Pinot Connection Failed
Symptoms: Connection refused, Broker unreachable, Network timeout
Cause: Invalid Pinot broker configuration or cluster not running
Solution:
- Verify PINOT_BROKER_HOST and PINOT_BROKER_PORT in .env file
- Check Pinot cluster is running and accessible
- Test connection: telnet <broker_host> <broker_port>
- Ensure firewall allows connections to Pinot broker
Environment Variables Not Loaded
Symptoms: Config missing errors, Default values being used
Cause: .env file not found or incorrectly formatted
Solution:
- Create .env file in repository root directory
- Copy from .env.example and modify values
- Ensure no spaces around = in variable assignments
- Restart MCP server after configuration changes
Claude Desktop Not Recognizing Server
Symptoms: Server not appearing, Connection errors in Claude
Cause: Incorrect claude_desktop_config.json configuration
Solution:
- Verify path to uv binary in command field
- Ensure correct path to mcp-pinot repository
- Restart Claude Desktop after configuration changes
- Check Claude Desktop logs for error messages
API Authentication Failed
Symptoms: 401 Unauthorized errors, Invalid API key message
Cause: Missing or incorrect API key
Solution:
- Verify API key is correctly copied from klavis.ai dashboard
- Check API key is set in environment variable or code
- Ensure API key has not expired
- Regenerate API key if necessary
OAuth Authorization Errors
Symptoms: OAuth redirect failures, Authentication loop, Token refresh errors
Cause: OAuth credentials not configured or expired
Solution:
- Complete OAuth authorization flow for required services
- Check redirect URLs are correctly configured
- Verify OAuth app credentials in service provider settings
- Contact Klavis support for OAuth troubleshooting
Tool Call Failures
Symptoms: Tool not found errors, Execution timeouts, Rate limit errors
Cause: Tool not properly configured or service rate limits exceeded
Solution:
- Verify tool name matches available tools list
- Check service-specific rate limits and quotas
- Ensure required parameters are provided correctly
- Review Klavis API logs for detailed error messages
Context Window Overload
Symptoms: Too many tools error, Context length exceeded, Slow responses
Cause: Too many tools exposed to AI agent at once
Solution:
- Use Strata Progressive Discovery to expose tools hierarchically
- Reduce number of simultaneous MCP servers in Strata configuration
- Filter tools based on current task context
- Enable intelligent tool filtering in Strata settings
Docker Deployment Issues
Symptoms: Container fails to start, Port conflicts, Connection refused
Cause: Docker configuration or port binding errors
Solution:
- Ensure Docker is installed and running
- Check port 5000 is not already in use (or change port mapping)
- Verify Docker image pulled successfully
- Check container logs: docker logs <container-id>
Apache Pinot not appearing in Klavis AI
Symptoms: Server not listed, Tools not available
Cause: Configuration or installation issue
Solution:
- Verify configuration syntax
- Check Apache Pinot installation
- Restart Klavis AI
- Check logs for error messages
Next Steps
Now that Apache Pinot is integrated with Klavis AI:
- Explore all Apache Pinot capabilities through Klavis AI
- Check out other MCP servers that work with Klavis AI
- Join the MCP community for tips and support
- Consider contributing to Apache Pinot development
Need Help?
- Search for Apache Pinot documentation
- Check the Klavis AI MCP guide
- Join the MCP community discussions