A lightweight, read-only-by-default PostgreSQL MCP server for data analysts and ETL developers
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"pg-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
<div align="center"> <img src="https://raw.githubusercontent.com/andre-c-andersen/pg-mcp/refs/heads/master/assets/postgres-mcp-lite.png" alt="Postgres MCP Lite Logo" width="600"/> [](https://opensource.org/licenses/MIT) [](https://pypi.org/project/pg-mcp/) [](https://x.com/AndreCAndersen) [](https://github.com/andre-c-andersen/pg-mcp/graphs/contributors) <h3>A lightweight, read-only-by-default Postgres MCP server for data analysts and ETL developers.</h3> </div> ## Overview **Postgres MCP Lite** is a lightweight, open-source Model Context Protocol (MCP) server for PostgreSQL, designed specifically for **data analysts and ETL developers** who need to explore and understand database schemas and data. This is a streamlined fork of [postgres-mcp](https://github.com/crystaldba/postgres-mcp) by [Crystal DBA](https://www.linkedin.com/company/crystaldba/), focused on **safe data exploration** rather than database administration: - **🔍 Data Exploration** - Understand database schemas, table structures, and relationships with AI assistance - **📊 Query Analysis** - Generate and execute SQL queries to analyze data patterns and relationships - **🛡️ Read-Only by Default** - Defaults to restricted mode with SQL validation, preventing accidental modifications - **🔌 Multiple [Transports](https://modelcontextprotocol.io/docs/concepts/transports)** - Supports both stdio and SSE - **🌐 Multi-Database Support** - Connect to multiple databases simultaneously (app, ETL, analytics, etc.) **Perfect for:** - 📈 Data analysts exploring production databases safely - 🔄 ETL developers understanding source and target schemas - 🤖 AI-assisted data discovery and documentation - 📝 Generating data analys…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.