PostgreSQL
PG-MCP is a PostgreSQL Model Context Protocol server that enables AI agents to discover, connect to, query, and understand PostgreSQL databases through a resource-oriented architecture. It extends the reference Postgres MCP implementation with multi-database support, rich catalog information extraction, extension context for PostGIS and pgVector, query execution plan analysis, and robust connection management. The server exposes database schema resources, data access capabilities, and specialized tools for executing read-only SQL queries, all while maintaining security through connection ID abstraction and read-only transaction enforcement. Built with Python 3.13 and asyncpg, it's particularly valuable for developers and data analysts who need AI assistants to interact with PostgreSQL databases without exposing sensitive connection details.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/stuzero/pg-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve PostgreSQL from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.