# Agentwork

> Use this tool when you need to delegate tasks to AI agents and oversee their progress with human-in-the-loop control. Agentwork solves problems of automated task management, providing a platform for creating tasks, monitoring status, and approving or rejecting plans and solutions. It accepts task inputs and returns status updates and solution outputs through a hosted remote endpoint with SSE transport.

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

## Description

Provides task delegation to AI agents through the Agentwork platform. Supports creating tasks, polling status, responding to agent questions, and approving or rejecting plans and solutions with human-in-the-loop oversight. Available as a hosted remote endpoint with SSE transport.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/agentwork)

## 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": "agentwork"
    }
  }
}
```

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