AI-powered MCP server for Apache Druid cluster management and analytic
AI-powered MCP server for Apache Druid cluster management and analytic
A comprehensive Model Context Protocol (MCP) server for Apache Druid that provides extensive tools, resources, and prompts for managing and analyzing Druid clusters.
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:
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| getDatasources | List all available Apache Druid datasources or get detailed schema for a specific datasource. |
| getLookups | Get configuration or status of lookups for all or a specific tier. |
| getSegments | Fetch segments metadata or details for a specific segment. |
| getSegmentLoadQueue | Get the load queue status showing segments currently being loaded. |
| queryDruidSql | Execute a SQL query against Druid datasources. |
| getCompactionConfig | View compaction configuration or configuration change history for datasources. |
| getCompactionStatus | Retrieve the current status of compaction runs and progress. |
| manageCompaction | Add, update, or remove a compaction configuration. |
| manageDatasourceOrSegment | Modify segment states or permanently drop a datasource. |
| manageLookup | Create, update, or delete a lookup configuration. |
| queryDruidMultiStage | Execute a multi-stage SQL query (MSQ) against Druid datasources as a task. |
| queryDruidMultiStageWithContext | Execute a multi-stage SQL query with custom context parameters. |
| getMultiStageQueryTaskStatus | Get the status of a multi-stage query task. |
| cancelMultiStageQueryTask | Cancel a running multi-stage query task. |
| getRetentionRules | Retrieve retention rules or audit history for a specific datasource or all datasources. |
| manageRetentionRules | Update retention rules configuration for a specific datasource. |
| submitIngestion | Submit a Druid ingestion specification or generate a simple batch template. |
| getSupervisors | List all supervisors or query details of a specific supervisor. |
| manageSupervisor | Suspend, resume, or terminate a supervisor's execution. |
| getTasks | List ingestion tasks matching specific states. |
| getTaskDetails | Fetch detailed information, specifications, execution reports, or execution logs for a task. |
| shutdownTask | Kill/shutdown a Druid task. |
| getClusterStatus | Check overall health or fetch specific metadata/properties from coordinators or routers. |
| getNodesStatus | List registered servers, their detailed status, or single node status. |
| diagnoseCluster | Perform automated diagnostic health checks, configuration audits, or query performance analysis. |
| checkFunctionalityHealth | Validate operations of ingestion systems, supervisor state transitions, and historical query latency. |
| manageAuthentication | Administer basic security users and credentials. |
| manageAuthorization | Manage security authorization properties, roles, and resource access policies. |
| manageSecurityAssignments | Configure mapping rules assigning roles to users, or retrieve the configured authenticator chains. |
{
"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": "YOUR_DRUID_AUTH_PASSWORD",
"DRUID_SSL_ENABLED": "false",
"DRUID_SSL_SKIP_VERIFICATION": "true"
}
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
| Variable | Description | Required |
|---|---|---|
| DRUID_ROUTER_URL | Declared in the maintainer’s client configuration. | Check documentation |
| DRUID_COORDINATOR_URL | Declared in the maintainer’s client configuration. | Check documentation |
| DRUID_AUTH_USERNAME | Declared in the maintainer’s client configuration. | Check documentation |
| DRUID_AUTH_PASSWORD | Declared in the maintainer’s client configuration. | Check documentation |
| DRUID_SSL_ENABLED | Declared in the maintainer’s client configuration. | Check documentation |
| DRUID_SSL_SKIP_VERIFICATION | Declared in the maintainer’s client configuration. | Check documentation |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
This repository holds the documentation and the registry manifest (server.json). The server itself is hosted — there is nothing to install.
Paid tools for HTML, JSON, shopping data and agent configs. Free discovery; $5 prepaid credits.
A Model Context Protocol (MCP) server that connects OmniFocus to Claude and other MCP-compatible AI assistants.
Vehicle specs, federal recalls, and OBD-II DTC reference for AI agents via MCP.