intermediate⏱️ 14-24 minutes📅 Updated June 2026

Step-by-step guide to integrate Apache Pinot MCP server with NVIDIA Agent Intelligence Toolkit. Includes table management and segment management.

Apache Pinot + NVIDIA Agent Intelligence Toolkit: 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 NVIDIA Agent Intelligence Toolkit, 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 NVIDIA Agent Intelligence Toolkit, 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 NVIDIA Agent Intelligence Toolkit
  • 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
  • NVIDIA Agent Intelligence Toolkit installed and configured
  • Compatible operating system (Python Package (pip), Docker Container, Framework Integration)

Installation

Step 1: Install Apache Pinot

Configuration

Step 2: Configure NVIDIA Agent Intelligence Toolkit

  1. Open NVIDIA Agent Intelligence Toolkit settings
  2. Navigate to MCP server configuration
  3. Add Apache Pinot server with appropriate settings
  4. Save and restart if needed

Examples

Once configured, you can use Apache Pinot in NVIDIA Agent Intelligence Toolkit:

List All Tables

Get overview of available Pinot tables

Ask NVIDIA Agent Intelligence Toolkit: "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 NVIDIA Agent Intelligence Toolkit: "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 NVIDIA Agent Intelligence Toolkit: "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 NVIDIA Agent Intelligence Toolkit: "Create a histogram showing user activity distribution by hour"

Expected Result: Histogram visualization with data aggregated by time buckets

Testing Your Setup

  1. Launch NVIDIA Agent Intelligence Toolkit
  2. Verify Apache Pinot is available in the tools list
  3. 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:

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

MCP Server Connection Failed

Symptoms: Connection refused errors, Timeout connecting to MCP server, URL not responding

Cause: MCP server not running or incorrect URL configuration

Solution:

  • Verify MCP server is running and accessible
  • Check URL in configuration matches server endpoint
  • Ensure network/firewall allows connection to server port
  • Test connection with curl or browser before agent integration

Tool Schema Validation Errors

Symptoms: Invalid input format errors, Schema mismatch warnings, Type validation failures

Cause: Input data does not match MCP tool schema

Solution:

  • Use CLI to inspect tool schema: aiq info mcp --url <url> --tool <name>
  • Validate input data matches expected types and required fields
  • Check JSON schema definitions in MCP server documentation
  • Convert inputs to proper format (dict, JSON string, or schema instance)

Framework Integration Issues

Symptoms: Import errors, Framework not found, Incompatible versions

Cause: Missing or incompatible framework dependencies

Solution:

  • Ensure target framework (LangChain, LlamaIndex, etc.) is installed
  • Check version compatibility between AIQ toolkit and framework
  • Install framework-specific dependencies as needed
  • Refer to documentation for framework-specific configuration

Performance Bottlenecks

Symptoms: Slow agent responses, High token usage, Workflow timeouts

Cause: Inefficient tool usage or workflow design

Solution:

  • Enable observability to identify bottlenecks
  • Use profiling features to analyze tool and agent performance
  • Review token tracking metrics to optimize LLM calls
  • Consider hyperparameter tuning for agent optimization

OpenTelemetry Integration Errors

Symptoms: Observability data not appearing, Telemetry export failures, Missing metrics

Cause: OpenTelemetry not properly configured

Solution:

  • Verify OpenTelemetry collector is running
  • Check observability configuration in AIQ settings
  • Ensure proper instrumentation of agent workflows
  • Review OpenTelemetry export settings and endpoints

Apache Pinot not appearing in NVIDIA Agent Intelligence Toolkit

Symptoms: Server not listed, Tools not available

Cause: Configuration or installation issue

Solution:

  • Verify configuration syntax
  • Check Apache Pinot installation
  • Restart NVIDIA Agent Intelligence Toolkit
  • Check logs for error messages

Next Steps

Now that Apache Pinot is integrated with NVIDIA Agent Intelligence Toolkit:

  • Explore all Apache Pinot capabilities through NVIDIA Agent Intelligence Toolkit
  • Check out other MCP servers that work with NVIDIA Agent Intelligence Toolkit
  • Join the MCP community for tips and support
  • Consider contributing to Apache Pinot development

Need Help?

Related Resources

More Integrations

Explore other MCP servers that work with NVIDIA Agent Intelligence Toolkit

Need Help?

Join the MCP community for support and discussions

Apache Pinot + NVIDIA Agent Intelligence Toolkit: MCP Setup Guide (2026)