# declaw-cli

> declaw-cli — declaw-ai-declaw-cli. Use this tool when you need to securely sandbox AI agents, protecting against potential security threats and vulnerabilities. The declaw-cli provides a command-line interface for managing sandboxed environments, accepting input parameters for customization and outputting secured AI agent configurations. Utilize declaw-cli when deploying AI agents in sensitive or high-risk environments, ensuring a robust security posture.

Canonical page: https://skillsregistry.net/skills/declaw-ai-declaw-cli  
JSON: https://api.skillsregistry.net/v1/skills/declaw-ai-declaw-cli

## Description

Command-line interface for Declaw — security-first sandboxing for AI agents

## Trust

- **Trust score (0–1):** 0.62
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/declaw-ai/declaw-cli)

## 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": "declaw-ai-declaw-cli"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/declaw-ai-declaw-cli` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/declaw-ai-declaw-cli/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