Doris

v1.0.0Databasesstable

init

doris-mcp-server-demomcpai-integration
Share:
9
Stars
0
Downloads
0
Weekly
0/5

What is Doris?

Doris is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to init

init

This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • init

Use Cases

Interact with Doris database system through MCP.
FreeOnePlus

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 7, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx doris-mcp-server-demo

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Doris

The Doris MCP Server provides a natural language to SQL (NL2SQL) interface for Apache Doris, a high-performance analytical database. It exposes tools for generating, validating, optimizing, and executing SQL queries, and follows a seven-step pipeline—from query parsing and example retrieval through execution and result analysis—making Doris accessible directly from AI assistants like Claude.

Prerequisites

  • Python 3.9 or later and pip
  • A running Apache Doris cluster (FE host accessible on port 9030 by default)
  • Git to clone the repository
  • A .env file configured with your Doris connection details
  • Optional: write access to a ./logs and ./data directory for metadata caching
1

Clone the repository

Pull the doris-mcp-server source from GitHub.

git clone https://github.com/FreeOnePlus/doris-mcp-server.git
cd doris-mcp-server
2

Install Python dependencies

Install all required packages from the requirements file.

pip install -r requirements.txt
3

Configure the environment file

Copy the example env file and fill in your Doris connection details and server preferences.

cp .env.example .env

# Edit .env with your values:
# DB_HOST=your-doris-fe-host
# DB_PORT=9030
# DB_USER=root
# DB_PASSWORD=your-password
# DB_DATABASE=your_database
# SERVER_HOST=0.0.0.0
# SERVER_PORT=3000
# LOG_LEVEL=INFO
4

Start the MCP server

Launch the server using the provided startup script. It will begin listening for MCP connections over SSE on the configured port.

./start_server.sh
5

Add to Claude Desktop configuration

Register the Doris MCP server in your Claude Desktop config. Since it uses SSE transport, provide the full server URL.

{
  "mcpServers": {
    "doris": {
      "command": "python",
      "args": ["-m", "doris_mcp_server"],
      "env": {
        "DB_HOST": "localhost",
        "DB_PORT": "9030",
        "DB_USER": "root",
        "DB_PASSWORD": "your-password",
        "DB_DATABASE": "your_database"
      }
    }
  }
}

Doris Examples

Client configuration

Claude Desktop config passing Doris connection details via environment variables.

{
  "mcpServers": {
    "doris": {
      "command": "python",
      "args": ["-m", "doris_mcp_server"],
      "env": {
        "DB_HOST": "localhost",
        "DB_PORT": "9030",
        "DB_USER": "root",
        "DB_PASSWORD": "yourpassword",
        "DB_DATABASE": "sales_db",
        "LOG_LEVEL": "INFO"
      }
    }
  }
}

Prompts to try

Natural language prompts that exercise the NL2SQL pipeline.

- "Show me the top 10 customers by total order value this quarter"
- "Generate SQL to find all products with inventory below 50 units"
- "Explain the query plan for: SELECT * FROM orders WHERE status = 'pending'"
- "Validate this SQL for syntax errors and security issues: DROP TABLE users"
- "List all available schemas in the connected Doris database"

Troubleshooting Doris

Connection refused on port 9030

Verify the Doris FE (Frontend) node is running and that DB_HOST and DB_PORT in your .env point to the correct host. The MySQL-compatible port is 9030 by default; check the Doris FE configuration if it differs.

Metadata refresh is slow on startup

Set FORCE_REFRESH_METADATA=false in .env after the first successful run. Cached metadata in the ./data directory is reused across restarts, significantly speeding up subsequent launches.

generate_sql tool returns incorrect SQL for complex queries

Use the find_similar_examples tool first to provide context, then call generate_sql. Adding example queries to the examples cache in ./data improves generation accuracy for domain-specific schemas.

Frequently Asked Questions about Doris

What is Doris?

Doris is a Model Context Protocol (MCP) server that init It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Doris?

Follow the installation instructions on the Doris GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Doris?

Doris works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Doris free to use?

Yes, Doris is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Databases MCP Servers

Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "doris-mcp-server-demo": { "command": "npx", "args": ["-y", "doris-mcp-server-demo"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Doris?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides