# ActionDock

> ActionDock — app-actiondock-actiondock. Use this tool when you need to securely integrate AI agents with external APIs, requiring human oversight and approval for actions. ActionDock solves the problem of uncontrolled AI-driven API interactions by providing a supervised gateway with policy enforcement and execution receipts. It accepts AI-generated API requests as input and outputs approved and executed actions with verifiable receipts.

Canonical page: https://skillsregistry.net/skills/app-actiondock-actiondock  
JSON: https://api.skillsregistry.net/v1/skills/app-actiondock-actiondock

## Description

Supervised API-write gateway for AI agents with policy, human approval and execution receipts.

## Trust

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

## Facts

- **Version:** 0.2.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Updated:** 2026-09-10

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/app.actiondock%2Factiondock)

## Use it

MCP endpoint published by the skill: `https://actiondock.app/mcp`

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": "app-actiondock-actiondock"
    }
  }
}
```

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