# QueryShield

> Use this tool when you need to securely interface AI agents with SQL databases, protecting against malicious queries and data breaches. QueryShield translates natural language to safe SQL, validates queries, and enforces row-level security, providing a secure and auditable interface for AI agents to access database information. It is ideal for use cases requiring controlled and monitored database access, such as data analysis or information retrieval tasks.

Canonical page: https://skillsregistry.net/skills/bch1212-queryshield  
JSON: https://api.skillsregistry.net/v1/skills/bch1212-queryshield

## Description

Secure SQL proxy for AI agents. Translates natural language to safe SQL via Claude, validates at the AST level (SELECT-only, no DDL/DML), enforces per-agent row-level security, and audit-logs every query.

## Trust

- **Trust score (0–1):** 0.47
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/aci99jsco5)
- **Repository:** <https://github.com/bch1212/queryshield>

## 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": "bch1212-queryshield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bch1212-queryshield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bch1212-queryshield/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