Apache Druid MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DRUID_URL | No | Druid router/broker URL | http://localhost:8888 |
| DRUID_TIMEOUT | No | Request timeout in milliseconds | 30000 |
| DRUID_PASSWORD | No | Authentication password (required for most production clusters) | |
| DRUID_USERNAME | No | Authentication username (required for most production clusters) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_sql_queryB | Execute a SQL query against Apache Druid and return results |
| list_datasourcesA | Get a list of all available datasources in Druid |
| get_datasource_metadataA | Get detailed metadata for a specific datasource including schema, size, and segments |
| test_connectionB | Test connection to the Druid cluster |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Cluster Status | Current status and health of the Druid cluster |
| All Datasources | List of all available datasources in the cluster |
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose: querying, listing datasources, retrieving metadata for a specific datasource, and testing connectivity. No overlapping or ambiguous responsibilities.
All tool names follow a consistent verb_noun pattern in snake_case (execute_sql_query, list_datasources, get_datasource_metadata, test_connection). The naming is predictable and homogeneous.
With exactly 4 tools, the server is well-scoped for a focused Druid integration. Each tool addresses a core need without unnecessary bloat or minimalism.
The tool surface covers the essential workflows for a Druid MCP server: testing connectivity, exploring datasources, inspecting metadata, and executing SQL queries. There are no obvious gaps for the intended use case.