# pg-semantic-mcp

> pg-semantic-mcp — chncaesar-pg-semantic-mcp. Use this tool when you need to leverage a PostgreSQL database for AI coding tasks, as it provides read-only access to database schema and sample data through a semantic search interface powered by large language models (LLMs) and customizable user-authored semantic layers. This tool solves problems related to database exploration, data discovery, and code generation by providing an intuitive and informative interface for AI agents. It accepts natural language queries as input and returns relevant database schema and data outputs, making it ideal for use cases involving data-driven coding and development.

Canonical page: https://skillsregistry.net/skills/chncaesar-pg-semantic-mcp  
JSON: https://api.skillsregistry.net/v1/skills/chncaesar-pg-semantic-mcp

## Description

A read-only PostgreSQL MCP server for AI coding agents that exposes database schema and sample data as tools, with LLM-powered semantic search enriched by a user-authored semantic layer.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/t68nkp2h0t)
- **Repository:** <https://github.com/chncaesar/db-semantic-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "chncaesar-pg-semantic-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/chncaesar-pg-semantic-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/chncaesar-pg-semantic-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt