通过只读MCP工作流查询Postgres数据库，使用PGMCP
Connect an MCP-compatible assistant to an existing PostgreSQL database for safe natural-language querying, schema-aware SQL, and streamed results.
Prerequisites
PostgreSQL, DATABASE_URL, optional OpenAI API key, MCP-compatible client
Installation
Use the upstream install or setup path that matches your environment:
- brew tap subnetmarco/homebrew-tap
- brew install pgmcp
- docker run -e DATABASE_URL="postgres://user:pass@host:5432/db" \
Requirements and caveats from upstream:
- ### Docker/Kubernetes
- # Docker
- # Integration tests (requires PostgreSQL)
Basic usage or getting-started notes:
- PGMCP connects to your existing PostgreSQL database and makes it accessible to AI assistants through natural language queries.
- PostgreSQL database (existing database with your schema)
- OpenAI API key (optional, for AI-powered SQL generation)
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/subnetmarco/pgmcp/HEAD/README.md
Documentation
- https://github.com/1991513ccie-png/skills
