# MCP Secrets

> Use this tool when you need to securely manage sensitive data and credentials for Large Language Models (LLMs) executing CLI commands. It solves problems related to protecting sensitive information and controlling access to credentials, with use cases including secure command execution and output redaction. The tool accepts credentials and command inputs, and provides redacted outputs and user-approved session permissions through an encrypted vault and macOS menu bar app interface.

Canonical page: https://skillsregistry.net/skills/henghonglee-mcp-secrets  
JSON: https://api.skillsregistry.net/v1/skills/henghonglee-mcp-secrets

## Description

A secure secrets management server that enables LLMs to execute CLI commands using injected credentials while protecting sensitive data through output redaction and user-approved session permissions. It features an encrypted vault, secret capture from command outputs, and a macOS menu bar app for native notifications and dialogs.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/k8xpz3k6ln)
- **Repository:** <https://github.com/henghonglee/claude-secrets>

## 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": "henghonglee-mcp-secrets"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/henghonglee-mcp-secrets` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/henghonglee-mcp-secrets/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