# warrant

> warrant — mariaangelikabuilds-warrant. Use this tool when you need to control and audit AI agent interactions with external systems, ensuring that actions are authorized and tracked. The warrant tool acts as a gateway, refusing unauthorized actions and creating an auditable record of decisions. It is ideal for use cases requiring secure, compliant, and transparent AI decision-making.

Canonical page: https://skillsregistry.net/skills/mariaangelikabuilds-warrant  
JSON: https://api.skillsregistry.net/v1/skills/mariaangelikabuilds-warrant

## Description

An MCP server that acts as an authorization gateway between an AI agent and external systems, deterministically refusing actions that exceed granted authority and sealing every decision into an auditable chain of custody.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/iz2frfzyb5)
- **Repository:** <https://github.com/mariaangelikabuilds/warrant>

## 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": "mariaangelikabuilds-warrant"
    }
  }
}
```

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