# hush

> Use this tool when you need to securely store and manage sensitive information for AI agents, solving problems related to data privacy and security. Hush provides a secret store where the agent never sees the plaintext, ensuring confidentiality and integrity of the data. It is ideal for use cases where sensitive data needs to be protected from unauthorized access, with secure input and output interfaces for encrypted data handling.

Canonical page: https://skillsregistry.net/skills/com-royashbrook-hush  
JSON: https://api.skillsregistry.net/v1/skills/com-royashbrook-hush

## Description

A secret store for AI agents: the agent never sees the plaintext.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.3.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-06-29

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/com.royashbrook%2Fhush)
- **Repository:** <https://github.com/royashbrook/hush>

## Use it

MCP endpoint published by the skill: `https://royashbrook.com/hush`

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": "com-royashbrook-hush"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/com-royashbrook-hush` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/com-royashbrook-hush/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