imply-druid-mcp: MCP Tool for Druid DB Query with AI Assistants like Claude

Imply Druid MCP

A read - only MCP server for Imply Cloud/Druid databases, supporting querying and exploring Druid data via AI assistants such as Claude, and providing functions for SQL queries, table management, dashboard, and dataset operations.

Database Developer tools #Druid query #Data exploration #Read - only service #AI assistant .Python

rating : 2 points

downloads : 5.0K

update time : 2025-12-30

Open Site

What is the Imply Druid MCP server?

This is a bridge server that connects AI assistants (such as Claude) with the Imply Druid database. It allows you to query the database using natural language, view table structures, explore data cubes and dashboards without writing complex SQL statements or using professional tools.

How to use the Imply Druid MCP server?

First, configure the server connection in Claude Desktop, and then you can directly ask Claude questions about the database. For example, you can ask 'Show all tables' or 'Query the top 10 records of sales data', and Claude will automatically call the corresponding tools to obtain the results.

Applicable scenarios

Suitable for users such as data analysts, business personnel, and product managers who need to quickly query and analyze data in the Druid database. Particularly suitable for scenarios where users need to query frequently but do not want to learn complex SQL syntax, or need to quickly explore the data structure and content.

Main features

SQL query execution

Supports both synchronous and asynchronous SQL queries. Synchronous queries return results immediately, suitable for small datasets; asynchronous queries are suitable for large datasets and return a query ID for subsequent result retrieval.

Query management

You can check the query status, obtain query results, and cancel running queries to comprehensively manage your database query tasks.

Table operations

List all tables (data sources) in the project and view the detailed structure information of each table, including field names, data types, etc.

Dashboard operations

Browse all dashboards in the Imply project and view the detailed configuration and content of the dashboards to help you understand the existing data visualizations.

Data cube operations

List all data cubes, view detailed information such as cube dimensions and metrics, and support querying data cubes using Pivot SQL syntax.

Advantages

Natural language interaction: Query the database using simple natural language without SQL expertise

Rapid exploration: Quickly browse the database structure, tables, and dashboards to understand the overall data situation

Asynchronous processing: Supports asynchronous queries for large datasets to avoid long waiting times

Easy integration: Easily integrate into Claude Desktop with simple configuration

Read-only security: Only provides query functions and will not accidentally modify or delete data

Limitations

Read-only operations: Unable to create, modify, or delete tables, data, or users

Requires API key: Need to configure the API key or access token of Imply Cloud

Network-dependent: Requires a stable network connection to access the Imply Cloud service

Query length limit: There is a maximum length limit for SQL queries (default 10000 characters)

Specific platform: Primarily targeted at Imply Cloud/Druid and not applicable to other databases

How to use

Install the server

Install the Imply Druid MCP server using uvx, pip, or pipx. It is recommended to use uvx as it automatically manages the virtual environment.

Configure environment variables

Set the necessary environment variables, including the organization name, region, cloud provider, project ID, and API key. This information can be obtained from the Imply Cloud console.

Configure Claude Desktop

Add the MCP server configuration to the Claude Desktop configuration file, specifying the command, parameters, and environment variables.

Start using

Restart Claude Desktop, and then you can start querying your Druid database using natural language.

Usage examples

Explore the database structure

When you first start working on a Druid project, you can quickly understand what tables and data structures are in the database.

Quick data query

When you need to view sample data in a table or perform a simple query, you can directly describe it in natural language.

Analyze data cubes

When there are predefined data cubes in the project, you can quickly query and analyze multi - dimensional data.

Check query status

When you have executed a long - running asynchronous query, you can check the query progress at any time.

Frequently Asked Questions

Do I need an Imply Cloud account to use this server?

Can this server modify the data in the database?

Will the query time out when querying large datasets?

Where can I find my project ID and API key?

Which cloud providers does this server support?

What should I do if the query fails?

Related resources

Official documentation of the MCP protocol

Understand the detailed specifications and design concepts of the Model Context Protocol

Imply Cloud documentation

The official documentation of Imply Cloud, including API references and user guides

Apache Druid official website

The official website of the Apache Druid real - time analytics database

GitHub repository

The source code and latest version of the Imply Druid MCP server

PyPI project page

The project page on the Python Package Index, including installation instructions and version history

🚀 imply-druid-mcp

A read-only MCP (Model Context Protocol) server for Imply Cloud/Druid databases. Query and explore your Druid data through Claude and other AI assistants.

🚀 Quick Start

imply-druid-mcp is a read - only MCP server that enables you to query and explore Druid data via Claude and other AI assistants. You can start using it after installation and configuration.

✨ Features

Supported ✅

SQL Query Execution
- Synchronous query execution
- Asynchronous query execution (for large datasets)
Query Management
- Check query status
- Retrieve query results
- Cancel running queries
Table Operations
- List all tables in project
- Get table schema details
Dashboard Operations
- List all dashboards
- Get dashboard details
Data Cube Operations
- List all data cubes
- Get data cube details
- Execute Pivot SQL queries

Not Supported ❌

Data Ingestion
Table/Schema Creation or Modification
User/Permission Management
Supervisor Management

🛠️ Tools

Query Tools

Tool	Description
`execute_sql_query`	Execute a SQL query synchronously and return results immediately
`execute_async_query`	Execute a SQL query asynchronously for large datasets. Returns a query ID
`get_query_results`	Retrieve results from an async query using query ID
`get_query_status`	Check the execution status of an async query
`cancel_query`	Cancel a running async query

Table Tools

Tool	Description
`list_tables`	List all tables (datasources) in the Druid project
`get_table_schema`	Get detailed schema information for a specific table

Dashboard Tools

Tool	Description
`list_dashboards`	List all dashboards in the Imply project
`get_dashboard`	Get detailed information about a specific dashboard

Data Cube Tools

Tool	Description
`list_data_cubes`	List all data cubes in the Imply project
`get_data_cube`	Get detailed data cube information including dimensions and measures
`query_data_cube`	Execute Pivot SQL query against a data cube

🗺️ API Mapping

This MCP server maps to the Imply Polaris API:

MCP Tool	Imply API Endpoint
`execute_sql_query`	`POST /v1/projects/{projectId}/query/sql`
`execute_async_query`	`POST /v1/projects/{projectId}/query/sql/statements`
`get_query_results`	`GET /v1/projects/{projectId}/query/sql/statements/{queryId}/results`
`get_query_status`	`GET /v1/projects/{projectId}/query/sql/statements/{queryId}`
`cancel_query`	`DELETE /v1/projects/{projectId}/query/sql/statements/{queryId}`
`list_tables`	`GET /v1/projects/{projectId}/tables`
`get_table_schema`	`GET /v1/projects/{projectId}/tables/{tableName}`
`list_dashboards`	`GET /v1/projects/{projectId}/dashboards`
`get_dashboard`	`GET /v1/projects/{projectId}/dashboards/{dashboardId}`
`list_data_cubes`	`GET /v1/projects/{projectId}/data-cubes`
`get_data_cube`	`GET /v1/projects/{projectId}/data-cubes/{cubeName}`
`query_data_cube`	`POST /v0/projects/{projectId}/pivot/data-cube-sql/query`

📦 Installation

Using uvx (Recommended)

uvx imply-druid-mcp

Using pip

pip install imply-druid-mcp
imply-druid-mcp

Using pipx

pipx install imply-druid-mcp
imply-druid-mcp

⚙️ Configuration

Property	Required	Default	Details
`IMPLY_ORGANIZATION`	Yes	-	Imply Cloud organization name
`IMPLY_REGION`	Yes	-	Region (e.g., `us-east-1`)
`IMPLY_CLOUD_PROVIDER`	Yes	-	Cloud provider: `aws`, `gcp`, or `azure`
`IMPLY_PROJECT_ID`	Yes	-	Imply project ID
`IMPLY_API_KEY`	Yes*	-	Imply API key
`IMPLY_ACCESS_TOKEN`	Yes*	-	OAuth access token (alternative)
`LOG_LEVEL`	No	`INFO`	Logging level
`DEFAULT_QUERY_TIMEOUT_MS`	No	`30000`	Default query timeout (ms)
`MAX_QUERY_LENGTH`	No	`10000`	Maximum SQL query length

*Either IMPLY_API_KEY or IMPLY_ACCESS_TOKEN is required.

🖥️ Claude Desktop Setup

Add to your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "imply-druid": {
      "command": "uvx",
      "args": ["imply-druid-mcp"],
      "env": {
        "IMPLY_ORGANIZATION": "your-org",
        "IMPLY_REGION": "us-east-1",
        "IMPLY_CLOUD_PROVIDER": "aws",
        "IMPLY_PROJECT_ID": "your-project-id",
        "IMPLY_API_KEY": "your-api-key"
      }
    }
  }
}

💻 Usage Examples

Basic Usage

User: Show me all tables in my Druid project

Claude: [Uses list_tables]
- wikipedia (datasource)
- events (datasource)
- metrics (datasource)

User: Query the top 10 records from wikipedia table

Claude: [Uses execute_sql_query with "SELECT * FROM wikipedia LIMIT 10"]
[Results displayed]

User: Show me all data cubes

Claude: [Uses list_data_cubes]
- sales_cube: Sales Analytics (source: sales_table)
- events_cube: Events Tracking (source: events)

User: Query the sales data cube for top cities

Claude: [Uses query_data_cube with Pivot SQL syntax]
SELECT "DIM:city" AS "City", MEASURE_BY_ID('total_sales') AS "Sales"
FROM "datacube"."sales_cube"
ORDER BY 2 DESC
LIMIT 10

🛠️ Development

git clone https://github.com/yeongbin-hwang/imply-druid-mcp.git
cd imply-druid-mcp
pip install -e ".[dev]"

📄 License

MIT License - see LICENSE for details.

📚 Resources

Notion Api MCP

Certified

A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.

Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.

The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.

TypeScript

20.3K

4.3 points

Duckduckgo MCP Server

Certified

The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.

Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.

UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.

27.2K

5 points

Gmail MCP Server

A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.

Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.

TypeScript

84.6K

4.7 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご

Imply Druid MCP

Overview

Installation

Content Details

Alternatives

What is the Imply Druid MCP server?

How to use the Imply Druid MCP server?

Applicable scenarios

Main features

How to use

Usage examples

Frequently Asked Questions

Related resources

Installation

🚀 imply-druid-mcp

🚀 Quick Start

✨ Features

Supported ✅

Not Supported ❌

🛠️ Tools

Query Tools

Table Tools

Dashboard Tools

Data Cube Tools

🗺️ API Mapping

📦 Installation

Using uvx (Recommended)

Using pip

Using pipx

⚙️ Configuration

🖥️ Claude Desktop Setup

💻 Usage Examples

Basic Usage

🛠️ Development

📄 License

📚 Resources

Alternatives