Apache Doris Mcp Server

Created By
Dorisa year ago
Doris MCP (Model Control Panel) Server is a backend service built with Python and FastAPI. It implements the MCP (Model Control Panel) protocol, allowing clients to interact with it through defined "Tools". It's primarily designed to connect to Apache Doris databases, potentially leveraging Large Language Models (LLMs) for tasks like converting natural language queries to SQL (NL2SQL), executing queries, and performing metadata management and analysis.
Overview

What is Apache Doris MCP Server?

Apache Doris MCP Server is a backend service built with Python and FastAPI that implements the Model Control Panel (MCP) protocol, allowing clients to interact with it through defined tools. It is primarily designed to connect to Apache Doris databases and can leverage Large Language Models (LLMs) for tasks such as converting natural language queries to SQL (NL2SQL), executing queries, and performing metadata management and analysis.

How to use Apache Doris MCP Server?

To use the Apache Doris MCP Server, clone the repository, install the dependencies, configure the environment variables, and run the service. Clients can connect to the server's SSE or Streamable HTTP endpoints to send requests and invoke the server's tools.

Key features of Apache Doris MCP Server?

  • Implements the MCP protocol with standard interfaces for tool calls and resource management.
  • Supports multiple communication modes: SSE, Streamable HTTP, and optional Stdio.
  • Provides a tool-based interface for database interaction, including SQL execution and metadata retrieval.
  • Flexible configuration via a .env file for database connections and server settings.
  • Capable of extracting database metadata information.

Use cases of Apache Doris MCP Server?

  1. Executing SQL queries directly against Apache Doris databases.
  2. Retrieving metadata about databases and tables.
  3. Managing and analyzing database resources through a standardized interface.

FAQ from Apache Doris MCP Server?

  • Can the MCP Server connect to other databases?
    Yes, it is designed to connect primarily to Apache Doris but can be adapted for other compatible databases.

  • Is there a graphical interface for the MCP Server?
    No, the MCP Server is designed for programmatic access through its API endpoints.

  • How do I configure the server?
    Configuration is done through a .env file where you can set database connection details and server parameters.

Server Config

{
  "mcpServers": {
    "doris-mcp": {
      "command": "uv",
      "args": [
        "--project",
        "/path/to/your/doris-mcp-server",
        "run",
        "doris-mcp-server"
      ],
      "env": {
        "DB_HOST": "FE_HOST",
        "DB_PORT": "9030",
        "DB_USER": "root",
        "DB_PASSWORD": ""
      }
    },
    "doris-http": {
      "url": "http://127.0.0.1:3000/mcp"
    }
  }
}
Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Doris
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago