# Agent Inbox

> Agent Inbox — zijian-ni-agent-inbox. Use this tool when you need to ensure AI agents' actions are reviewed and approved by humans before execution, solving problems of unintended or unauthorized actions. The Agent Inbox takes in proposed actions from AI agents and outputs approved or denied actions based on human input, with a timeout feature to prevent stalled decisions. It is ideal for use cases requiring strict control and oversight of AI-driven decisions.

Canonical page: https://skillsregistry.net/skills/zijian-ni-agent-inbox  
JSON: https://api.skillsregistry.net/v1/skills/zijian-ni-agent-inbox

## Description

A local human-in-the-loop gate for AI agents that blocks actions until human approval, with timeout defaulting to denial.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xuq5stzvb7)
- **Repository:** <https://github.com/Zijian-Ni/agent-inbox>

## 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": "zijian-ni-agent-inbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/zijian-ni-agent-inbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/zijian-ni-agent-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