Apache Druid
This MCP server provides AI assistants with direct access to Apache Druid cluster operations through 40+ specialized tools covering data querying, ingestion management, cluster monitoring, and administrative tasks. Built by iunera using Java Spring Boot with the Spring AI MCP framework, it connects to Druid's REST APIs with support for SSL/TLS, basic authentication, and both STDIO and SSE transport modes, offering tools for SQL query execution including multi-stage queries, datasource and segment management, supervisor and task control, retention policy configuration, lookup management, compaction operations, and health monitoring with diagnostic capabilities. The implementation includes configurable prompt templates for operational guidance, Docker containerization, extensive integration tests with mock and real Druid clusters, and supports both development and production deployments with security configurations, making it valuable for data engineering workflows, cluster administration, and building AI assistants that need programmatic access to Druid analytics databases without manual web console navigation.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/iunera/druid-mcp-server
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Apache Druid from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp --scope user for --scope project to commit it to .mcp.json.