Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

mcp-doris

MCP.Pizza Chef: morningman

mcp-doris is an MCP server designed to integrate Apache Doris and VeloDB databases into the Model Context Protocol ecosystem. It allows LLMs and AI agents to query, interact with, and manage data stored in these analytic databases in real time, facilitating advanced data workflows and AI-driven data exploration. The server supports secure connection parameters and can be run locally for development and inspection.

Use This MCP server To

Query Apache Doris data directly from LLM-powered applications Enable real-time data exploration in VeloDB through AI agents Integrate analytic database queries into AI workflows Develop AI copilots that interact with large-scale analytic databases Automate report generation from Apache Doris datasets Build data-driven decision support tools using MCP and Doris Test and debug database queries via MCP Inspector UI

README

Apache Doris MCP Server

smithery badge

An MCP server for Apache Doris.

Demo

Usage

Cursor

Name: doris
Type: command
Command: DORIS_HOST=<doris-host> DORIS_PORT=<port> DORIS_USER=<doris-user> DORIS_PASSWORD=<doris-pwd> uv run --with mcp-doris --python 3.13 mcp-doris

Development

Prerequest

  • install uv

Run MCP Inspector

cd /path/to/mcp-doris
uv sync
source .venv/bin/activate
export PYTHONPATH=/path/to/mcp-doris:$PYTHONPATH
env DORIS_HOST=<doris-host> DORIS_PORT=<port> DORIS_USER=<doris-user> DORIS_PASSWORD=<doris-pwd> mcp dev mcp_doris/mcp_server.py

Then visit http://localhost:5173 in web browser.

Publish

uv build
uv publish

mcp-doris FAQ

How do I connect mcp-doris to my Apache Doris instance?
Set environment variables DORIS_HOST, DORIS_PORT, DORIS_USER, and DORIS_PASSWORD before running the server.
Can mcp-doris be used with VeloDB as well?
Yes, mcp-doris supports both Apache Doris and VeloDB databases for MCP integration.
What development tools are required to run mcp-doris locally?
You need to install 'uv' (Astral's CLI tool) and Python 3.13 to run and develop mcp-doris.
How can I inspect and debug queries with mcp-doris?
Use the MCP Inspector by running the server locally and visiting http://localhost:5173 in your browser.
Is mcp-doris compatible with multiple LLM providers?
Yes, it works with any MCP-compatible LLM provider such as OpenAI, Anthropic Claude, and Google Gemini.
How do I publish a new version of mcp-doris?
Use 'uv build' followed by 'uv publish' commands to build and publish the server package.
Does mcp-doris support secure authentication?
Yes, it uses standard environment variables for user credentials to securely connect to the database.
Can I extend mcp-doris for custom query commands?
Yes, as an MCP server, it can be extended with additional commands and functionality as needed.