# safe-postgres-mcp

> safe-postgres-mcp — lucasoresi-mcp-local-optacost. Use this tool when you need to securely explore and query PostgreSQL databases in a read-only mode, ensuring data protection and preventing unauthorized modifications. It solves problems related to data security and compliance by enforcing multiple layers of protection, including privilege audits and lexical guards. The tool accepts database queries as input and provides outputs such as query results, table listings, and schema descriptions.

Canonical page: https://skillsregistry.net/skills/lucasoresi-mcp-local-optacost  
JSON: https://api.skillsregistry.net/v1/skills/lucasoresi-mcp-local-optacost

## Description

An MCP server for safe read-only PostgreSQL exploration and querying, enforced by three independent layers: startup privilege audit, lexical guard, and read-only transactions. Offers tools for querying, table listing, schema description, relationship mapping, and query explanation.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/p26a8gt7g8)
- **Repository:** <https://github.com/lucasoresi/mcp-local-optacost>

## 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": "lucasoresi-mcp-local-optacost"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/lucasoresi-mcp-local-optacost` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/lucasoresi-mcp-local-optacost/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
