# hub_tasks

列出 hub 上最近的任务（状态、agent、耗时、提示词摘要）。

Agent View of the PolicyLayer registry record for `hub_tasks`. HTML page: https://policylayer.com/tools/a2a-hub/hub-tasks

## Facts

- Tool: `hub_tasks`
- Server: A2a Hub (`bodazi-na/a2a-hub`) — https://policylayer.com/tools/a2a-hub.md
- Homepage: https://github.com/bodazi-na/a2a-hub
- Risk category: Write (Medium risk)
- Registry record: grade B, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "hub_tasks",
    "arguments": {}
  }
}
```

## Why hub_tasks is rated Medium

An AI agent can call hub_tasks faster than any human can review: one bad instruction and it creates or modifies resources in A2a Hub by the hundred, each call as confident as the last.

## Use case

AI agents use hub_tasks to create or update resources in A2a Hub, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your A2a Hub environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches A2a Hub:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "hub_tasks": {
      "limits": [
        {
          "counter": "hub_tasks_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on A2a Hub (5)

- `hub_status` — Read — https://policylayer.com/tools/a2a-hub/hub-status.md
- `hub_agents` — Write — https://policylayer.com/tools/a2a-hub/hub-agents.md
- `hub_plan` — Write — https://policylayer.com/tools/a2a-hub/hub-plan.md
- `hub_send` — Write — https://policylayer.com/tools/a2a-hub/hub-send.md
- `hub_trace` — Write — https://policylayer.com/tools/a2a-hub/hub-trace.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=a2a-hub · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/a2a-hub
