# AgentGate

> Use this tool when you need to implement human-in-the-loop approval for agent tool calls, ensuring secure and compliant decision-making. AgentGate solves the problem of unapproved or unauthorized actions by agents, providing a gateway for policy-based decisioning and human oversight via popular communication platforms. It accepts agent requests as input and outputs approved or denied actions, with a secure audit trail for compliance and security purposes.

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

## Description

Human-in-the-loop approval gateway for agent tool calls: agents request, policies decide, humans approve via Slack/Discord/web — with an OWASP-LLM-Top-10-tagged audit trail. Self-hostable.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** communication
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/psmzw3x2my)
- **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": "agentkitai-agentgate"
    }
  }
}
```

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