# Agent Vault

> Use this tool when you need to securely manage sensitive information for AI coding agents, enabling human-approved access to password manager secrets via MCP. It solves the problem of securely storing and retrieving secrets, such as passwords and API keys, while providing an approval workflow for access control. The Agent Vault takes in secret requests and outputs approved or denied access, making it ideal for use cases requiring secure and controlled secret management.

Canonical page: https://skillsregistry.net/skills/loonshoot-agent-vault  
JSON: https://api.skillsregistry.net/v1/skills/loonshoot-agent-vault

## Description

Human-in-the-loop secret access for AI coding agents, enabling approval workflow for password manager secrets via MCP.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/kolqc78j4n)
- **Repository:** <https://github.com/loonshoot/agent_vault>

## 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": "loonshoot-agent-vault"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/loonshoot-agent-vault` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/loonshoot-agent-vault/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