# evidra-lock

> evidra-lock — vitas-evidra-lock. Use this tool when you need to ensure secure and validated infrastructure operations for AI agents, providing a fail-closed kill-switch to prevent unauthorized executions. It solves problems of operational security and compliance by validating actions through evidence-backed checks. Inputting git-based infrastructure configurations, it outputs validated or blocked operations, ideal for use in high-stakes or sensitive AI deployments.

Canonical page: https://skillsregistry.net/skills/vitas-evidra-lock  
JSON: https://api.skillsregistry.net/v1/skills/vitas-evidra-lock

## Description

MCP Kill-switch for AI agents. Validates infrastructure operations before execution. Fail-closed. Evidence-backed.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** Apache-2.0
- **Updated:** 2026-09-20

## Source

- **Source listing:** [GitHub](https://github.com/vitas/evidra-lock)

## 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": "vitas-evidra-lock"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/vitas-evidra-lock` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/vitas-evidra-lock/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