# tool-use-firewall

> tool-use-firewall — reaatech-tool-use-firewall. Use this tool when you need to control and secure interactions between AI agents and MCP tools, enforcing policies such as cost caps and rate limits. It solves problems of unauthorized or malicious access, providing features like human-in-the-loop approval and full audit logging. It takes in agent requests and tool outputs, operating as a proxy to ensure compliant and safe operations.

Canonical page: https://skillsregistry.net/skills/reaatech-tool-use-firewall  
JSON: https://api.skillsregistry.net/v1/skills/reaatech-tool-use-firewall

## Description

Policy enforcement proxy between agents and MCP tools. Cost caps, rate limits, argument validation, human-in-the-loop approval for destructive ops, read-only mode, and full audit logging. MCP-native.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** monitoring
- **Updated:** 2026-09-22

## Source

- **Source listing:** [GitHub](https://github.com/reaatech/tool-use-firewall)

## 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": "reaatech-tool-use-firewall"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/reaatech-tool-use-firewall` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/reaatech-tool-use-firewall/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