Doris MCP Server Integration

What does “Doris” MCP Server do?

Doris MCP (Model Context Protocol) Server is a backend service built with Python and FastAPI designed to connect AI assistants and clients with Apache Doris databases. By implementing the MCP standard, it facilitates secure and efficient interactions between language models and external data sources. Doris MCP Server enables tasks such as converting natural language queries to SQL (NL2SQL), executing database queries, retrieving and managing metadata, and performing advanced monitoring and analytics. Its modular architecture includes dedicated managers for tools, prompts, and resources, making it a robust solution for enhancing data development workflows, automating database management, and integrating AI-driven insights into enterprise systems.

List of Prompts

• Intelligent prompt templates for data analysis
  (These are managed by the Prompts Manager and are designed to standardize LLM interactions for data analysis tasks. Specific templates are referenced but not listed individually in the available documentation.)

List of Resources

• Resource Management and Metadata Exposure
  (Exposes Doris database metadata and resources to AI clients via the Resources Manager.)
• Catalog Federation Support
  (Allows access to both internal Doris tables and external sources like Hive and MySQL.)
• Comprehensive Database Metadata
  (Provides detailed metadata extraction for use as LLM context.)
• Query Analytics Artifacts
  (Exports query explain and profiling results for LLM attachment and analysis.)

List of Tools

• Enhanced Monitoring Tools
  (Advanced memory tracking, metrics collection, and backend node discovery.)
• Query Information Tools
  (Provides SQL explain, profiling, and analytics features.)
• Tools Manager
  (Central tool registration and routing interface for orchestrating tool calls through MCP.)
• Resources Manager
  (Handles resource exposure and metadata management.)
• Prompts Manager
  (Manages and serves prompt templates for AI and LLM workflows.)

Use Cases of this MCP Server

• Natural Language to SQL (NL2SQL):
  Enables developers to convert human language queries into SQL statements for Doris databases, streamlining data access and analysis.
• Advanced Query Monitoring and Profiling:
  Provides in-depth SQL explain, performance profiling, and analytics tools, aiding in performance tuning and diagnostics.
• Metadata Exploration and Management:
  Allows AI-powered systems to explore database schemas, catalogs, and resources, supporting tasks like documentation generation or automated data mapping.
• Multi-Source Data Integration:
  Supports catalog federation, enabling seamless integration with external data sources (e.g., Hive, MySQL) for comprehensive analytics workflows.
• Secure Data Operations:
  Implements robust security, access control, and data masking, ensuring safe interactions between LLMs and sensitive enterprise data.

How to set it up

Windsurf

1. Ensure Python 3.12+ is installed.

2. Install the package:
   pip install mcp-doris-server@latest

3. Edit the Windsurf configuration file to add the Doris MCP server.

4. Insert the following snippet under mcpServers:

   {
     "doris-mcp": {
       "command": "mcp-doris-server",
       "args": []
     }
   }
   

5. Save and restart Windsurf.

6. Verify the server is running and accepting connections.

Claude

1. Install Python 3.12+.

2. Install the Doris MCP server:
   pip install mcp-doris-server@latest

3. Add the server to Claude’s configuration under mcpServers.

4. Use a JSON snippet like:

   {
     "doris-mcp": {
       "command": "mcp-doris-server",
       "args": []
     }
   }
   

5. Restart Claude and check integration.

Cursor

1. Ensure Python 3.12+ is installed.

2. Install the server:
   pip install mcp-doris-server@latest

3. In Cursor’s config, add:

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

4. Save configuration and restart Cursor.

5. Confirm the Doris MCP server connection.

Cline

1. Install Python 3.12+.

2. Install the Doris MCP server:
   pip install mcp-doris-server@latest

3. Update the Cline MCP configuration with:

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

4. Save the config and restart Cline.

5. Check the MCP server status.

Securing API Keys

Store sensitive credentials and API keys in environment variables. Example using .env:

{
  "env": {
    "DORIS_HOST": "your-doris-host",
    "DORIS_PORT": "your-port",
    "DORIS_USER": "username",
    "DORIS_PASSWORD": "password"
  },
  "inputs": {
    "database": "your-database"
  }
}

Ensure environment variables are referenced in your configuration for enhanced security.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "doris-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “doris-mcp” to the actual name of your MCP server and update the URL accordingly.

Overview

Based on the information above, the Doris MCP Server is well-documented in terms of features, resources, and setup. However, some details about prompt templates and sampling support are lacking or not explicitly listed, which slightly limits its completeness for advanced MCP workflows.

Our opinion

Given the strong presence of core MCP features, robust security and resource management, and clear setup guidance, the Doris MCP Server rates as an 8/10 for MCP protocol support and practical application. Gaps mainly relate to explicit prompt listings and lack of sampling/roots documentation.

MCP Score