Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

StarRocks MCP Server

Official StarRocks MCP server for SQL execution, database exploration, StarRocks resource templates, system information, table/database overviews, and Plotly chart generation.

by StarRocks·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • StarRocks MCP can execute SQL through `read_query` and DDL/DML through `write_query`.
  • The `write_query` tool is documented for CREATE, ALTER, DROP, INSERT, UPDATE, DELETE, and other commands that do not return a result set.
  • The `read_query` tool can write full query results to files when `output_file` is provided; relative paths use STARROCKS_MCP_OUTPUT_DIR, while absolute and home-relative paths bypass that directory.
  • Overview tools can sample rows, count rows, cache table summaries in memory, and return cached errors or stale summaries until refreshed.
  • The `query_and_plotly_chart` tool executes a SQL query and uses a Python Plotly expression to generate chart output from the result DataFrame.
  • Resource templates can expose database, table, proc, transaction, job, task, catalog, frontend, backend, and compute-node information.
  • SSE mode is documented as deprecated; prefer stdio or streamable HTTP with explicit network controls.

Privacy notes

  • StarRocks credentials, connection URLs, database names, table names, schemas, SQL text, query results, sample rows, proc output, generated chart images, errors, and output-file paths may be visible to the MCP client and model provider.
  • StarRocks datasets can contain customer records, telemetry, analytics, business metrics, security data, billing data, or other regulated information.
  • Output files created by `read_query` remain on the machine where the MCP server runs, which may be local for desktop clients or remote for HTTP deployments.
  • STARROCKS_URL, STARROCKS_PASSWORD, Keychain service names, database credentials, and generated result files should stay out of prompts, issues, logs, screenshots, and committed files.

Prerequisites

  • Python 3.10 or newer and uv available to the MCP client runtime.
  • StarRocks FE host, MySQL protocol port, database, username, and password.
  • Least-privilege StarRocks user with only the approved databases and operations.
  • Written policy for whether `write_query` may be used in the workspace.
  • Approved output directory when allowing `read_query` to write large results to disk.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
advanced
Tool listing metadata
Full copyable content
{
  "mcpServers": {
    "starrocks": {
      "command": "uv",
      "args": ["run", "--with", "mcp-server-starrocks", "mcp-server-starrocks"],
      "env": {
        "STARROCKS_HOST": "<starrocks-fe-host>",
        "STARROCKS_PORT": "9030",
        "STARROCKS_USER": "<least-privilege-user>",
        "STARROCKS_PASSWORD": "<starrocks-password>",
        "STARROCKS_DB": "<approved-database>",
        "MCP_TRANSPORT_MODE": "stdio",
        "STARROCKS_MCP_OUTPUT_DIR": "<approved-output-dir>"
      }
    }
  }
}

About this resource

Content

StarRocks MCP Server is the official StarRocks Model Context Protocol server for connecting Claude and other MCP clients to StarRocks databases. It supports SQL execution, database and table exploration, StarRocks resource templates, system information through proc paths, table and database overviews, and Plotly chart generation from query results.

The package is published as mcp-server-starrocks and exposes the mcp-server-starrocks command. The README documents stdio, HTTP, and streamable HTTP modes, while noting that SSE mode is deprecated and no longer maintained.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, README, PyPI metadata, package metadata, server entry point, implementation, and license for current install commands, transport modes, environment variables, tool behavior, resource templates, and licensing.

Features

  • Official StarRocks MCP server.
  • PyPI package mcp-server-starrocks.
  • Stdio, HTTP, streamable HTTP, and deprecated SSE transport modes.
  • read_query for SELECT, SHOW, DESCRIBE, and other result-returning commands.
  • write_query for DDL, DML, and other non-result commands.
  • analyze_query for query profile or explain-analyze output.
  • query_and_plotly_chart for SQL-backed Plotly chart generation.
  • table_overview and db_overview with row counts, schema details, sample rows, and in-memory caching.
  • starrocks:// resource templates for databases, tables, and schemas.
  • proc:// resource template for StarRocks internal system information.
  • Environment configuration through individual connection variables or STARROCKS_URL.
  • Optional macOS Keychain password lookup.

Installation

For local stdio usage with uv:

{
  "mcpServers": {
    "starrocks": {
      "command": "uv",
      "args": ["run", "--with", "mcp-server-starrocks", "mcp-server-starrocks"],
      "env": {
        "STARROCKS_HOST": "<starrocks-fe-host>",
        "STARROCKS_PORT": "9030",
        "STARROCKS_USER": "<least-privilege-user>",
        "STARROCKS_PASSWORD": "<starrocks-password>",
        "STARROCKS_DB": "<approved-database>",
        "MCP_TRANSPORT_MODE": "stdio",
        "STARROCKS_MCP_OUTPUT_DIR": "<approved-output-dir>"
      }
    }
  }
}

Use a dedicated StarRocks user with only the permissions needed for the workflow. Do not enable write_query workflows unless writes are intended and reviewed.

Use Cases

  • Ask Claude to inspect StarRocks databases and tables before drafting SQL.
  • Run reviewed SELECT queries for analytics and debugging.
  • Generate table or database overviews with schema details, row counts, and sample rows.
  • Analyze a query with profile or explain-analyze output.
  • Create a Plotly chart from an approved query result.
  • Explore StarRocks proc paths for frontend, backend, compute-node, transaction, job, task, and catalog information.
  • Write large read-query results to an approved output directory when model context is too small.

Safety and Privacy

StarRocks MCP is a database execution surface. Use least-privilege credentials, review generated SQL, and require explicit approval for write_query, DDL, DML, broad reads, output-file writes, proc inspection, and chart generation over sensitive datasets.

read_query can write files on the server host, and absolute paths bypass the configured output directory. Keep result paths controlled, avoid exposing production credentials, and treat generated charts and cached overviews as derived data that may reveal private rows or schema details.

Disclosure

StarRocks offers open-source and commercial analytics database products. This listing is not sponsored, paid, or affiliate-driven, and it is scoped to the source-backed official StarRocks MCP server.

Duplicate Check

No StarRocks MCP Server, StarRocks/mcp-server-starrocks, mcp-server-starrocks, or matching source URL entry was found in content/mcp, content/tools, content/guides, content/agents, or content/skills.

#starrocks#database#sql#analytics#visualization

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.