# Agent Inbox

> Agent Inbox — ai-clize-inbox. Use this tool when you need to manage email communications for AI agents, providing a secure and controlled environment for sending and receiving emails. The Agent Inbox solves problems related to email security and trust, allowing for human-approved sends and treating inbound emails as untrusted by default. It accepts email inputs and provides outputs in the form of received and sent emails, making it ideal for use cases where AI agents require email functionality with built-in security measures.

Canonical page: https://skillsregistry.net/skills/ai-clize-inbox  
JSON: https://api.skillsregistry.net/v1/skills/ai-clize-inbox

## Description

A real email inbox for AI agents: human-approved sends, untrusted-by-default inbound.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 0.26.1
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/ai.clize%2Finbox)
- **Repository:** <https://github.com/cooldk/clize-cli>

## 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": "ai-clize-inbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ai-clize-inbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ai-clize-inbox/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