Druid MCP server
{
"mcpServers": {
"iunera-druid": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/iunera/druid-mcp-server:2.0.1"
],
"env": {
"YOUR_JWT_TOKEN": "<your_jwt_token>",
"DRUID_ROUTER_URL": "https://...",
"DRUID_COORDINATOR_URL": "https://..."
}
}
}
}{
"mcpServers": {
"iunera-druid": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/iunera/druid-mcp-server:2.0.1"
],
"env": {
"YOUR_JWT_TOKEN": "<your_jwt_token>",
"DRUID_ROUTER_URL": "https://...",
"DRUID_COORDINATOR_URL": "https://..."
}
}
}
}{
"mcpServers": {
"iunera-druid": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/iunera/druid-mcp-server:2.0.1"
],
"env": {
"YOUR_JWT_TOKEN": "<your_jwt_token>",
"DRUID_ROUTER_URL": "https://...",
"DRUID_COORDINATOR_URL": "https://..."
}
}
}
}{
"servers": {
"iunera-druid": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/iunera/druid-mcp-server:2.0.1"
],
"env": {
"YOUR_JWT_TOKEN": "${input:your_jwt_token}",
"DRUID_ROUTER_URL": "${input:druid_router_url}",
"DRUID_COORDINATOR_URL": "${input:druid_coordinator_url}"
}
}
},
"inputs": [
{
"id": "your_jwt_token",
"type": "promptString",
"description": "Your jwt token",
"password": true
},
{
"id": "druid_router_url",
"type": "promptString",
"description": "Druid router url",
"password": true
},
{
"id": "druid_coordinator_url",
"type": "promptString",
"description": "Druid coordinator url",
"password": true
}
]
}{
"mcpServers": {
"iunera-druid": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"docker.io/iunera/druid-mcp-server:2.0.1"
],
"env": {
"YOUR_JWT_TOKEN": "<your_jwt_token>",
"DRUID_ROUTER_URL": "https://...",
"DRUID_COORDINATOR_URL": "https://..."
}
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 2.0.1
What it does
An MCP server that exposes Apache Druid cluster management and analytics capabilities through tools, resources, and prompts. Designed for developers and data engineers who need to interact with Druid clusters programmatically or through natural language interfaces.
- Query and analyze time series data in Apache Druid using natural language through AI assistants.
- Manage Druid cluster operations including data ingestion, datasource configuration, and health monitoring.
- Explore Druid metadata and execute administrative tasks via tools integrated into LLM clients.
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.