AnalyticDB PostgreSQL MCP Server

Name: AnalyticDB PostgreSQL MCP Server
Author: aliyun

@aliyun

Repository

About AnalyticDB PostgreSQL MCP Server

No overview available yet

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "alibabacloud-adbpg-mcp-server": {
      "command": "uv",
      "args": [
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

Execute SELECT SQL queries on the AnalyticDB PostgreSQL server

Execute DML (INSERT, UPDATE, DELETE) SQL queries on the AnalyticDB PostgreSQL server

Execute DDL (CREATE, ALTER, DROP) SQL queries on the AnalyticDB PostgreSQL server

Collect table statistics

Get query execution plan

** Upload a text file (with its name) and file content to graphrag to generate a knowledge graph.

** Query the graphrag using the specified query string and mode。

** Add LLM long memory.

** Retrieves all memory records associated with a specific user, run or agent.

** Retrieves memories relevant to the given query for a specific user, run, or agent.

Overview

What is AnalyticDB PostgreSQL MCP Server?

AnalyticDB PostgreSQL MCP Server is a universal interface between AI Agents and AnalyticDB PostgreSQL databases. It enables seamless communication for AI Agents to retrieve database metadata and execute SQL operations.

How to use AnalyticDB PostgreSQL MCP Server?

Install via PyPI (pip install adbpg-mcp-server) or from source. Run in stdio (default) or HTTP transport mode, configured via environment variables for database connection and optional graphRAG/LLM memory services. Integrate with MCP clients by adding the server configuration to the client's config file.

Key features of AnalyticDB PostgreSQL MCP Server

Execute SELECT, DML, and DDL SQL queries
Analyze table statistics and explain query plans
Upload and query graphRAG knowledge graphs
Manage decision trees (upload, append, delete)
Store, search, and delete LLM long-term memory
Retrieve schemas, tables, DDL, and statistics via resources

Use cases of AnalyticDB PostgreSQL MCP Server

AI agents querying database metadata and running SQL operations
Building conversational agents that interact with AnalyticDB PostgreSQL
Enabling GraphRAG-based knowledge graph insights with database context
Integrating LLM memory persistence for personalized AI interactions
Automated database schema exploration and performance analysis

FAQ from AnalyticDB PostgreSQL MCP Server

What are the runtime dependencies?

Python 3.11 or higher and the uv package manager for environment and package management.

What transport modes are supported?

Stdio (default) for standard MCP client integration, and Streamable‑HTTP for REST‑based access, testing, or debugging.

How do I authenticate HTTP endpoints?

Set the MCP_AUTH_TOKEN environment variable or use the --auth-token CLI argument. Clients must include the Authorization: Bearer <token> header.

What tools does the server provide?

SQL execution tools (SELECT, DML, DDL), table analysis, query explain, graphRAG upload/query, decision tree management, and LLM memory add/search/delete.