# AgentGate

> Use this tool when you need to ensure safe and controlled decision-making in AI workflows, particularly for sensitive actions that require human oversight. AgentGate solves the problem of unchecked AI autonomy by providing a real-time approval gateway for consequential steps, taking in agent requests and outputting human-approved decisions. It is ideal for use cases where explicit sign-off is necessary to mitigate risks and ensure compliance.

Canonical page: https://skillsregistry.net/skills/agentgate  
JSON: https://api.skillsregistry.net/v1/skills/agentgate

## Description

Provides a human-in-the-loop approval gateway for AI agents over MCP. Agents request approval for sensitive actions, and humans decide in real time — enabling safe agentic workflows where consequential steps require explicit sign-off.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentgate)
- **Repository:** <https://github.com/agentkitai/agentgate>

## 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": "agentgate"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/agentgate` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/agentgate/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