Manage Apache Druid Clusters with AI

Druid MCP Server

A comprehensive Model Context Protocol (MCP) server for Apache Druid that provides extensive tools, resources, and prompts for managing and analyzing Druid clusters.

Developed by iunera - Advanced AI and Data Analytics Solutions

Overview

This MCP server implements a intend-based architecture where profiles picture their usaae intend and the corresponding area of Druid usage. The server provides three main types of MCP components:

• Tools - Executable functions for performing operations
• Resources - Data providers for accessing information
• Prompts - AI-assisted guidance templates

Video Walkthrough

Learn how to integrate AI agents with Apache Druid using the MCP server. This tutorial demonstrates time series data exploration, statistical analysis, and data ingestion using natural language with AI assistants like Claude, ChatGPT, and Gemini.

Click the thumbnail above to watch the video on YouTube

🌊 Y̊pipe: AI-Powered UI for Druid

Experience your data like never before with Y̊pipe (formerly Data-Philter), a local desktop application that makes offline AI practical, designed by iunera. It leverages this Druid MCP Server to provide a seamless, conversational interface for your Druid cluster.

• Natural Language Queries: Ask questions in plain English and get results instantly.
• Local & Secure: Runs completely locally with support for offline models (CPU/GPU).
• Plug & Play: Works out-of-the-box with the Development Druid Installation.

Get Ypipe on GitHub →

The easiest way to test iunera/druid-mcp-server is ypipe.com / https://github.com/iunera/ypipe

📋 Ypipe Integration Blueprint

For seamless integration, we provide a predefined Ypipe integration blueprint file:

• Blueprint File: druid.ypipe
• Configuration Guide: Ypipe Example Documentation

This blueprint allows you to easily connect and configure the Druid MCP server in Ypipe through a visual workspace.

Ypipe Workspace Flow	Druid Node Configuration

Features

• Pure Java
• Spring AI MCP Server integration
• Tool-based architecture for MCP protocol compliance
• Tool-based Architecture: Complete MCP protocol compliance with automatic JSON schema generation
• Multiple Transport Modes: STDIO, SSE, and Streamable HTTP support including Oauth
• Real-time Communication: Server-Sent Events with streaming capabilities
• Comprehensive error handling
• Customizable Prompt Templates: AI-assisted guidance with template customization
• Comprehensive Error Handling: Graceful error handling with meaningful responses
• Enterprise Ready: Production-grade configuration and security features

MCP Inspector Interface

When connected to an MCP client, you can inspect the available tools, resources, and prompts through the MCP inspector interface:

Available Tools

The tools interface shows all available Druid management functions organized by feature areas including data management, ingestion management, and monitoring & health.

Available Resources

The resources interface displays all accessible Druid data sources and metadata that can be retrieved through the MCP protocol.

Available Prompts

The prompts interface shows all AI-assisted guidance templates available for various Druid management tasks and data analysis workflows.

Quick Start

MCP Configuration for LLMs

A ready-to-use MCP configuration file is provided at mcp-servers-config.json that can be used with LLM clients to connect to this Druid MCP server.

Examples

The configuration includes multiple integration and transport options:

• STDIO (default): see examples/stdio/README.md - server is spawned by the MCP client over STDIO.
• Streamable HTTP (profile: http): see examples/streamable-http/README.md - single /mcp endpoint per MCP 2025-06-18.
• Ypipe Blueprint: see examples/ypipe/README.md - configure and run the Druid MCP Server inside the Ypipe desktop client using the druid.ypipe blueprint.

Docker examples using environment variables:

# STDIO mode (default)
docker run --rm -i \
  -e DRUID_ROUTER_URL=http://your-druid-router:8888 \
  -e DRUID_COORDINATOR_URL=http://your-druid-coordinator:8081 \
  iunera/druid-mcp-server:latest

# HTTP mode (enable profile 'http' and expose /mcp)
docker run -p 8080:8080 \
  -e SPRING_PROFILES_ACTIVE=http,query \
  -e DRUID_ROUTER_URL=http://your-druid-router:8888 \
  -e DRUID_COORDINATOR_URL=http://your-druid-coordinator:8081 \
  iunera/druid-mcp-server:latest

Note on Spring profiles:

• Default profile: stdio,query
• HTTP profile: set SPRING_PROFILES_ACTIVE=http,query to enable Streamable HTTP at /mcp

Prerequisites

• Java 25
• Maven 3.6+
• Apache Druid cluster running with router on port 8888

Build and Run

# Build the application
mvn clean package -DskipTests

# Run the application
java -jar target/druid-mcp-server-2.0.1.jar

The server will start on port 8080 by default.

For detailed build instructions, testing, Docker setup, and development guidelines, see development.md.

Security & Authentication

• Streamable HTTP and SSE transports are secured with OAuth 2.0 by default.
• Clients must send a valid Bearer token in the Authorization header when connecting.
• Example: Authorization: Bearer YOUR_JWT_TOKEN

Environment Variables

• DRUID_MCP_SECURITY_OAUTH2_ENABLED:
  • Description: Enables or disables OAuth2 security for client authentication.
  • Type: Boolean
  • Default: true (OAuth2 is enabled by default as per the text above)
  • Usage: Set to false to disable OAuth2 authentication. When disabled, clients can access the server without providing OAuth2 tokens.

• For enterprise SSO integration (OpenID Connect, Azure AD, Keycloak, etc.), please send an inquiry to consulting@iunera.com and see Contact & Support.

Installation from Maven Central

If you prefer to use the pre-built JAR without building from source, you can download and run it directly from Maven Central.

Prerequisites

• Java 25 JRE only

Download and Run

Download the JAR from Maven Central https://repo.maven.apache.org/maven2/com/iunera/druid-mcp-server/

# STDIO mode (default)
java -jar target/druid-mcp-server-2.0.1.jar

# HTTP mode (profile: http) - exposes /mcp on port 8080
java -Dspring.profiles.active=http \
     -jar target/druid-mcp-server-2.0.1.jar

For Developers

For detailed development information including build instructions, testing guidelines, architecture details, and contributing guidelines, see development.md.

Available Tools by Feature

The MCP server activates tools dynamically based on active Spring profiles (SPRING_PROFILES_ACTIVE). The default configuration runs the server in STDIO mode with the query profile enabled.

Profile: query (Default Active Profile)

Provides safe, read-only data querying and browsing capabilities.

Profile: ops

Provides administrative control over ingestion specs, tasks, streaming supervisors, retention rules, and compaction.

Profile: permissions

Provides basic security authentication and authorization administration.

Profile: health

Provides active health checking, cluster status, diagnostics, and doctor recommendation scans.

Available Resources by Feature

Available Prompts by Feature

Environment Variables Configuration

The application can be configured using environment variables, which is the recommended approach for production environments. Below is a comprehensive list of supported environment variables derived from the application.yaml configuration file.

Druid Connection

• DRUID_ROUTER_URL: The URL of the Druid router.
• DRUID_AUTH_USERNAME: The username for Druid authentication.
• DRUID_AUTH_PASSWORD: The password for Druid authentication.
• DRUID_SSL_ENABLED: Enables or disables SSL for Druid connections (true/false).
• DRUID_SSL_SKIP_VERIFICATION: Skips SSL certificate verification (true/false).
• DRUID_MCP_SQL_SYNTAX_CORRECTION_ENABLED: Enables or disables automatic SQL syntax correction (default: true). When enabled, automatically formats queries, corrects casing, and quotes identifiers for Druid.
• DRUID_MCP_SQL_SYNTAX_CORRECTION_CACHE_TTL_MS: The Time-To-Live (TTL) in milliseconds for the cached table and column metadata loaded from Druid (default: 300000 / 5 minutes).

MCP Server Configuration

• DRUID_MCP_SECURITY_OAUTH2_ENABLED: Enables or disables OAuth2 security for HTTP client authentication (true/false).
• SPRING_PROFILES_ACTIVE: Comma-separated list of profiles to activate (e.g. query, ops, permissions, health for tools capabilities, or http to enable HTTP server transport instead of default STDIO).
• SPRING_AI_MCP_SERVER_NAME: The name of the MCP server.
• SPRING_AI_MCP_SERVER_PROTOCOL: The protocol used by the MCP server (e.g., streamable).

General Server Configuration

• SERVER_PORT: The port the server listens on.
• SERVER_SERVLET_SESSION_COOKIE_NAME: The name of the session cookie.
• SPRING_APPLICATION_NAME: The name of the application.
• SPRING_CONFIG_IMPORT: Imports additional configuration files.
• SPRING_MAIN_BANNER_MODE: The mode for the startup banner (e.g., off).

Logging

• LOGGING_FILE_NAME: The name of the log file.
• LOGGING_LEVEL_ORG_SPRINGFRAMEWORK_SECURITY: The log level for Spring Security (e.g., DEBUG).

SSL-Encrypted Cluster with Authentication

This section provides comprehensive guidance on connecting to SSL-encrypted Druid clusters with username and password authentication.

Prerequisites

• SSL-enabled Druid cluster with HTTPS endpoints
• Valid username and password credentials for Druid authentication
• SSL certificates properly configured (or ability to skip verification for testing)

Configuration Methods

Method 1: Environment Variables (Recommended for Production)

Set the following environment variables before starting the MCP server:

# Druid cluster URL with HTTPS
export DRUID_ROUTER_URL="https://your-druid-cluster.example.com:8888"

# Authentication credentials
export DRUID_AUTH_USERNAME="your-username"
export DRUID_AUTH_PASSWORD="your-password"

# SSL configuration
export DRUID_SSL_ENABLED="true"
export DRUID_SSL_SKIP_VERIFICATION="false"  # Use "true" only for testing

# Start the MCP server
java -jar target/druid-mcp-server-2.0.1.jar

Method 2: Runtime System Properties

Pass configuration as JVM system properties:

java -Ddruid.router.url="http://localhost:8888" \
     -Ddruid.auth.username="admin" \
     -Ddruid.auth.password="password" \
     -jar target/druid-mcp-server-2.0.1.jar

SSL Configuration Options

Production SSL Setup

For production environments with valid SSL certificates:

export DRUID_ROUTER_URL="https://druid-prod.company.com:8888"
export DRUID_SSL_ENABLED="true"
export DRUID_SSL_SKIP_VERIFICATION="false"

The server will use the system's default truststore to validate SSL certificates.

Authentication Methods

The MCP server supports HTTP Basic Authentication with username and password:

• Username: Set via DRUID_AUTH_USERNAME or druid.auth.username
• Password: Set via DRUID_AUTH_PASSWORD or druid.auth.password

The credentials are automatically encoded using Base64 and sent with each request using the Authorization: Basic header.

MCP Client Configuration with SSL

Update your mcp-servers-config.json to include environment variables:

{
  "mcpServers": {
    "druid-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "DRUID_ROUTER_URL",
        "-e",
        "DRUID_COORDINATOR_URL",
        "-e",
        "DRUID_AUTH_USERNAME",
        "-e",
        "DRUID_AUTH_PASSWORD",
        "-e",
        "DRUID_SSL_ENABLED",
        "-e",
        "DRUID_SSL_SKIP_VERIFICATION",
        "iunera/druid-mcp-server:2.0.1"
      ],
      "env": {
        "DRUID_ROUTER_URL": "http://host.docker.internal:8888",
        "DRUID_COORDINATOR_URL": "http://host.docker.internal:8081",
        "DRUID_AUTH_USERNAME": "",
        "DRUID_AUTH_PASSWORD": "",
        "DRUID_SSL_ENABLED": "false",
        "DRUID_SSL_SKIP_VERIFICATION": "true"
      }
    }
  }
}

MCP Prompt Customization

The server provides extensive prompt customization capabilities through the prompts.properties file located in src/main/resources/.

Prompt Configuration Structure

The prompts.properties file contains:

1. Global Settings: Enable/disable prompts and set watermarks
2. Feature Toggles: Control which prompts are available
3. Custom Variables: Organization-specific information
4. Template Definitions: Full prompt templates for each feature

Overriding Prompts

You can override any prompt template using Java system properties with the -D flag:

Method 1: System Properties (Runtime Override)

java -Dprompts.druid-data-exploration.template="Your custom template here" \
     -jar target/druid-mcp-server-2.0.1.jar

Method 2: Custom Properties File

1. Create a custom properties file (e.g., custom-prompts.properties):

# Custom prompt template
prompts.druid-data-exploration.template=My custom data exploration prompt:\n\
1. Custom step one\n\
2. Custom step two\n\
{datasource_section}\n\
Environment: {environment}

2. Load it at runtime:

java -Dspring.config.additional-location=classpath:custom-prompts.properties \
     -jar target/druid-mcp-server-2.0.1.jar

Available Prompt Variables

All prompt templates support these variables:

Prompt Template Examples

Custom Data Exploration Prompt

prompts.druid-data-exploration.template=Welcome to {organizationName} Druid Analysis!\n\n\
Please help me explore our data:\n\
{datasource_section}\n\
Environment: {environment}\n\
Contact: {contactInfo}\n\n\
{watermark}

Custom Query Optimization Prompt

prompts.druid-query-optimization.template=Query Performance Analysis for {organizationName}\n\n\
Query to optimize: {query}\n\n\
Please provide:\n\
1. Performance bottleneck analysis\n\
2. Optimization recommendations\n\
3. Best practices for our {environment} environment\n\n\
{watermark}

Disabling Specific Prompts

You can disable individual prompts by setting their enabled flag to false:

mcp.prompts.data-exploration.enabled=false
mcp.prompts.query-optimization.enabled=false

Or disable all prompts globally:

mcp.prompts.enabled=false

MCP Integration

This server uses Spring AI's MCP Server framework and supports both STDIO and SSE transports. The tools, resources, and prompts are automatically registered and exposed through the MCP protocol.

Transport Modes

The Druid MCP Server supports multiple transport modes compliant with MCP 2025-06-18 specification:

Streamable HTTP Transport (Recommended)

The new Streamable HTTP transport provides enhanced performance and scalability with support for multiple concurrent clients:

# Default configuration with Streamable HTTP

java -Dspring.profiles.active=http \
     -jar target/druid-mcp-server-2.0.1.jar
# Server available at http://localhost:8080/mcp (configurable endpoint)

Features:

• Single Endpoint: One HTTP endpoint handles both POST and GET requests
• Multiple Clients: Support for concurrent client connections
• Optional SSE Streaming: Server-Sent Events for real-time updates
• Enhanced Security: Origin header validation and authentication
• Backwards Compatibility: Automatic fallback for older MCP clients
• Keep-alive: Configurable connection health monitoring

Security

• The Streamable HTTP and SSE modes are secured with OAuth by default. Your MCP client must obtain and send a valid bearer token when connecting.
• For enterprise SSO integration (OpenID Connect, Azure AD, Keycloak, etc.), please send an inquiry to consulting@iunera.com and see Contact & Support.

STDIO Transport (Command-line Integration)

Perfect for LLM clients and desktop applications:

java -jar target/druid-mcp-server-2.0.1.jar

Legacy SSE Transport (Deprecated)

Still supported for backwards compatibility. It is no longer the default and may be removed in a future version.

Note: The SSE endpoint is secured with OAuth by default. Clients must include a valid bearer token when connecting. For SSO integration support, see Contact & Support.

Metrics Collection

To enhance the product and understand usage patterns, this server collects anonymous usage metrics. This data helps prioritize new features and improvements. You can opt-out of anonymous metrics collection by setting the druid.mcp.metrics.enabled to `false.

🐳 Development Druid Installation

For local development, testing, and learning, a complete Docker Compose setup for running a full Apache Druid cluster is available at iunera/druid-local-cluster-installer.

This setup is the recommended way to get a Druid cluster running for use with this MCP server.

Key Features:

• Complete Druid Cluster: Includes all core Druid services (Coordinator, Broker, Historical, MiddleManager, Router).
• One-Command Install: Automated scripts for macOS, Linux, and Windows.
• Cross-Platform: Runs anywhere Docker is available.
• Pre-configured: Sensible defaults for local development.
• Basic Security Enabled: Pre-configured admin user (admin/password).
• Ready for Ypipe: Designed to work out-of-the-box with iunera/ypipe.

Related Projects

This Druid MCP Server is part of a comprehensive ecosystem of Apache Druid tools and extensions developed by iunera. These complementary projects enhance different aspects of Druid cluster management and data ingestion:

🔧 Druid Cluster Configuration

Advanced configuration management and deployment tools for Apache Druid clusters. This project provides:

• Automated Cluster Setup: Streamlined configuration templates for different deployment scenarios
• Configuration Management: Best practices and templates for production Druid clusters
• Deployment Automation: Tools and scripts for consistent cluster deployments
• Environment-Specific Configs: Optimized configurations for development, staging, and production environments

Integration with Druid MCP Server: The cluster configurations provided by this project work seamlessly with the monitoring and management capabilities of the Druid MCP Server, enabling comprehensive cluster lifecycle management.

📊 Code Ingestion Druid Extension

A specialized Apache Druid extension for ingesting and analyzing code-related data and metrics. This extension enables:

• Code Metrics Ingestion: Specialized parsers for code analysis data and software metrics
• Developer Analytics: Tools for analyzing code quality, complexity, and development patterns
• CI/CD Integration: Seamless integration with continuous integration and deployment pipelines
• Custom Data Formats: Support for various code analysis tools and formats

Integration with Druid MCP Server: This extension expands the ingestion capabilities that can be managed through the MCP server's ingestion management tools, providing specialized support for code analytics use cases.

Why Use These Together?

• Complete Ecosystem: From cluster setup to specialized data ingestion and management
• Consistent Architecture: All projects follow similar design principles and integration patterns
• Enhanced Capabilities: Each project extends different aspects of the Druid ecosystem
• Production Ready: Battle-tested configurations and extensions for enterprise deployments

Roadmap

• Druid Auto Compaction: Intelligent automatic compaction configuration
• MCP Auto Completion: Enhanced autocomplete functionality with sampling using McpComplete
• MCP Notifications: Real-time notifications for MCP operations
• Proper Observability: Comprehensive metrics and tracing
• Enhanced Monitoring: Advanced cluster monitoring and alerting capabilities
• Advanced Analytics: Machine learning-powered insights and recommendations
• Kubernetes Support: Proper deployment on Kubernetes

About iunera

This Druid MCP Server is developed and maintained by iunera, a leading provider of advanced AI and data analytics solutions.

iunera specializes in:

• AI-Powered Analytics: Cutting-edge artificial intelligence solutions for data analysis
• Enterprise Data Platforms: Scalable data infrastructure and analytics platforms (Druid, Flink, Kubernetes, Kafka, Spring)
• Model Context Protocol (MCP) Solutions: Advanced MCP server implementations for various data systems
• Custom AI Development: Tailored AI solutions for enterprise needs

As veterans in Apache Druid iunera deployed and maintained a large number of solutions based on Apache Druid in productive enterprise grade scenarios.

Need Expert Apache Druid Consulting?

Maximize your return on data with professional Druid implementation and optimization services. From architecture design to performance tuning and AI integration, our experts help you navigate Druid's complexity and unlock its full potential.

Get Expert Druid Consulting →

Need Enterprise MCP Server Development Consulting?

ENTERPRISE AI INTEGRATION & CUSTOM MCP (MODEL CONTEXT PROTOCOL) SERVER DEVELOPMENT

Iunera specializes in developing production-grade AI agents and enterprise-grade LLM solutions, helping businesses move beyond generic AI chatbots. They build secure, scalable, and future-ready AI infrastructure, underpinned by the Model Context Protocol (MCP), to connect proprietary data, legacy systems, and external APIs to advanced AI models.

Get Enterprise MCP Server Development Consulting →

For more information about our services and solutions, visit www.iunera.com.

examples/ypipe/README.md

Ypipe Integration Blueprint for Apache Druid

This folder contains the integration blueprint and configuration details for using this Druid MCP Server within Ypipe.

Ypipe is an AI-powered desktop client that lets you interact with your Apache Druid cluster in natural language, running models locally and securely.

What is druid.ypipe?

The druid.ypipe file is a predefined MCP Integration Blueprint (McpIntegrationBlueprint). It specifies how Ypipe should configure, run, and communicate with the Druid MCP Server. It details:

• Environment variables (e.g., DRUID_ROUTER_URL, DRUID_AUTH_USERNAME, DRUID_AUTH_PASSWORD) needed for connection.
• Service specifications to auto-build or download the server and map port options.
• Client schemas to facilitate smooth communication.

Screenshots

Below is the visual flow of the Druid MCP Integration inside Ypipe:

1. Integration Workspace Flow

This screenshot shows the workflow layout and integration nodes within the Ypipe dashboard.

2. Druid Node Details

This screenshot shows the configuration panel for the Apache Druid integration node in Ypipe, showing the host URL and authentication parameters.

How to Use

1. Ensure you have Ypipe installed.
2. Import or reference the druid.ypipe blueprint in your Ypipe configuration directory.
3. Configure your Druid connection details (such as your router URL and basic credentials) through the visual node setup in the Ypipe interface.
4. Interact with your Druid cluster using natural language chat, tools, resources, and custom prompts!

examples/stdio/README.md

STDIO Examples (JBang & Docker)

This folder contains examples for running the Druid MCP Server with the STDIO transport. These examples are designed to be used by MCP clients (e.g., Claude Desktop) that spawn the server process and communicate over STDIO.

Option 1: Running with JBang (Recommended)

JBang is the easiest way to run the server as it automatically manages the Java environment and downloads the required version.

Quick use with MCP client

Point your MCP client to this config file:

• mcpservers-jbang.json

The JBang configuration in that file allows the client to start the server directly using the Maven GAV.

Direct JBang run (optional)

export DRUID_ROUTER_URL=http://localhost:8888
export DRUID_AUTH_USERNAME=admin
export DRUID_AUTH_PASSWORD=password
jbang druid-mcp-server@iunera/druid-mcp-server

Option 2: Running with Docker

Docker is a great alternative if you prefer containerized execution.

Quick use with MCP client

Point your MCP client to this config file:

• mcpservers-docker.json

Direct Docker run (optional)

If your client does not support spawning via config, you can also run the server manually and point the client to the spawned process (stdin/stdout attached):

docker run --rm -i \
  -e DRUID_ROUTER_URL=http://host.docker.internal:8888 \
  -e DRUID_COORDINATOR_URL=http://host.docker.internal:8081 \
  -e DRUID_AUTH_USERNAME=admin \
  -e DRUID_AUTH_PASSWORD=password \
  iunera/druid-mcp-server:2.0.1

Tip: Replace DRUID_ROUTER_URL and add DRUID_AUTH_USERNAME/DRUID_AUTH_PASSWORD and TLS flags when connecting to a secured Druid.

examples/streamable-http/README.md

Streamable HTTP (Docker) Examples

This folder contains Docker-focused examples for running the Druid MCP Server with the Streamable HTTP transport (MCP 2025-06-18). Clients connect over HTTP to a single /mcp endpoint.

We focus on environment variable configuration. No Java/JAR commands are required.

Quick use with MCP client

Point your MCP client to this config file:

• mcpservers-streamable-http.json

This tells your client to connect to the Streamable HTTP endpoint. You must run the server container separately (see below).

Optional: Enable OAuth2 protection

1. Start the server with OAuth2 enabled:

docker run --rm -p 8080:8080 \
  -e SPRING_PROFILES_ACTIVE=http \
  -e DRUID_ROUTER_URL=http://host.docker.internal:8888 \
  -e DRUID_COORDINATOR_URL=http://host.docker.internal:8081 \
  -e DRUID_AUTH_USERNAME=admin \
  -e DRUID_AUTH_PASSWORD=password \
  iunera/druid-mcp-server:2.0.1

2. Obtain a token using client-credentials grant (default client: oidc-client / secret):

export MCP_OAUTH_TOKEN=$(curl -s -XPOST "http://localhost:8080/oauth2/token" \
  --data grant_type=client_credentials \
  --user "oidc-client:secret" | jq -r ".access_token")

The provided mcpservers-streamable-http.json will forward the token using the Authorization: Bearer header.

Streamable HTTP endpoint will be available at:

• http://localhost:8080/mcp

Adjust -p 8080:8080 if you need a different port.