# agent-safe-tools

> agent-safe-tools — wangke-112-agent-safe-tools. Use this tool when you need to safely inspect production logs or databases using natural language queries with your AI coding agent. It solves problems related to secure data access and query execution by providing read-only and blocked dangerous operations, ensuring production environments remain protected. Ideal for use cases where secure data inspection is required, with inputs including natural language queries and outputs including query results, all while keeping sensitive information safe.

Canonical page: https://skillsregistry.net/skills/wangke-112-agent-safe-tools  
JSON: https://api.skillsregistry.net/v1/skills/wangke-112-agent-safe-tools

## Description

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default, dangerous SQL/shell blocked, production disabled, no stored credentials. A recommended Skill layer teaches the model when and how to use them.

## Trust

- **Trust score (0–1):** 0.83
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** MIT
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/wangke-112/agent-safe-tools)

## 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": "wangke-112-agent-safe-tools"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wangke-112-agent-safe-tools` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wangke-112-agent-safe-tools/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