# Cloakbox

> Use this tool when you need to analyze sensitive data while protecting privacy and security. Cloakbox solves the problem of securely querying databases with personally identifiable information (PII) by creating a tokenized copy with provable numeric equivalence. It provides a safe interface for Large Language Models (LLMs) to input queries and receive anonymized outputs, ensuring sensitive data remains confidential.

Canonical page: https://skillsregistry.net/skills/mbufkin-cloakbox  
JSON: https://api.skillsregistry.net/v1/skills/mbufkin-cloakbox

## Description

Let LLMs analyze sensitive data safely by querying a tokenized, join-preserving copy of the database, with fail-closed PII scanning and provable numeric equivalence.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/zjozruutw7)
- **Repository:** <https://github.com/mbufkin/cloakbox>

## 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": "mbufkin-cloakbox"
    }
  }
}
```

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