Back to directory

Apache Doris MCP Server

An MCP server exposing read-only Apache Doris capabilities to AI agents, organized as eight stable domains with fifty-five progressively disclosed child tools covering catalog, query, cluster, ingestion, search, governance and lakehouse operations.

Apache Doris MCP Server

Apache Doris MCP Server replaced an earlier flat tool surface with eight domains — catalog, query, cluster, pipeline, search, governance, lakehouse and semantic — each exposing a small number of child capabilities that a host discovers progressively: calling a domain with no arguments returns its authorized children and exact schemas, and a follow-up call names the specific child tool, its arguments and a manifest version.

Version 1.0 is Generally Available for MCP protocol 2026-07-28 compatibility over Streamable HTTP and stdio on the master branch, though the Python package classifier itself remains Beta. Hosts that cannot use progressive disclosure can set an environment variable to expose all 55 children flatly instead, under collision-free names (this does not restore pre-1.0 tool aliases). It requires Python 3.12.

More in MCP servers

See all 734
  • Light Cloud

    light-cloud.com

    A hosting platform that deploys a static site, a container, or a managed Postgres database straight from a GitHub, GitLab, or Bitbucket push, with a preview URL for every branch and an MCP server for deploying from Claude Code.

  • ForensicDbg

    forensicdbg.com

    A post-mortem debugger for native Windows x86 and x64 crashes, with an MCP interface so AI tools can consume crash-dump analysis directly.

  • Karada.ai

    karada.ai

    A CI/CD platform that auto-compiles existing APIs into Go MCP servers, attaches composable middleware, and exposes them through one gateway usable from Cursor, Claude Code, and Windsurf.