# run_task

A execute tool on the 1point3acres Toolkit MCP server.

Agent View of the PolicyLayer registry record for `run_task`. HTML page: https://policylayer.com/tools/1point3acres-toolkit/run-task

## Facts

- Tool: `run_task`
- Server: 1point3acres Toolkit (`vivian-labs/1point3acres-toolkit`) — https://policylayer.com/tools/1point3acres-toolkit.md
- Homepage: https://github.com/vivian-labs/1point3acres-toolkit
- Risk category: Execute (High risk)
- Registry record: grade D, 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": "run_task",
    "arguments": {}
  }
}
```

## Why run_task is rated High

A tool that 'runs' tasks on behalf of an AI agent represents code execution with effects dependent on what task is passed to it. This is inherently Execute category. While the server itself is a routing/economics layer, the tool's ability to execute arbitrary tasks makes it high severity due to potential for misuse—an agent could be prompted to run malicious tasks.

From the tool's own definition: "Tool name 'run_task' combined with server purpose of routing AI tasks to models indicates execution of code or arbitrary operations. The description is empty, which limits certainty but the name and context suggest task execution capabilities."

## Use case

AI agents invoke run_task to trigger actions in 1point3acres Toolkit. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 1point3acres Toolkit:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_task": {
      "limits": [
        {
          "counter": "run_task_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 1point3acres Toolkit (32)

- `control_task` — Execute — https://policylayer.com/tools/1point3acres-toolkit/control-task.md
- `daily_run` — Execute — https://policylayer.com/tools/1point3acres-toolkit/daily-run.md
- `session_logout` — Execute — https://policylayer.com/tools/1point3acres-toolkit/session-logout.md
- `browse_board` — Read — https://policylayer.com/tools/1point3acres-toolkit/browse-board.md
- `collect_company` — Read — https://policylayer.com/tools/1point3acres-toolkit/collect-company.md
- `daily_history` — Read — https://policylayer.com/tools/1point3acres-toolkit/daily-history.md
- `daily_status` — Read — https://policylayer.com/tools/1point3acres-toolkit/daily-status.md
- `get_my_profile` — Read — https://policylayer.com/tools/1point3acres-toolkit/get-my-profile.md
- `get_thread_detail` — Read — https://policylayer.com/tools/1point3acres-toolkit/get-thread-detail.md
- `get_unread_count` — Read — https://policylayer.com/tools/1point3acres-toolkit/get-unread-count.md
- `interviews_search` — Read — https://policylayer.com/tools/1point3acres-toolkit/interviews-search.md
- `list_notifications` — Read — https://policylayer.com/tools/1point3acres-toolkit/list-notifications.md
- `list_tasks` — Read — https://policylayer.com/tools/1point3acres-toolkit/list-tasks.md
- `organize_thread` — Read — https://policylayer.com/tools/1point3acres-toolkit/organize-thread.md
- `react_to_notification` — Read — https://policylayer.com/tools/1point3acres-toolkit/react-to-notification.md
- `recognize_media` — Read — https://policylayer.com/tools/1point3acres-toolkit/recognize-media.md
- `reply_thread` — Read — https://policylayer.com/tools/1point3acres-toolkit/reply-thread.md
- `reply_to_notification` — Read — https://policylayer.com/tools/1point3acres-toolkit/reply-to-notification.md
- `runtime_info` — Read — https://policylayer.com/tools/1point3acres-toolkit/runtime-info.md
- `search_threads` — Read — https://policylayer.com/tools/1point3acres-toolkit/search-threads.md
- `session_status` — Read — https://policylayer.com/tools/1point3acres-toolkit/session-status.md
- `stripe_collect` — Read — https://policylayer.com/tools/1point3acres-toolkit/stripe-collect.md
- `task_status` — Read — https://policylayer.com/tools/1point3acres-toolkit/task-status.md
- `user_profile` — Read — https://policylayer.com/tools/1point3acres-toolkit/user-profile.md
- `archive_media` — Write — https://policylayer.com/tools/1point3acres-toolkit/archive-media.md
- `create_collection_task` — Write — https://policylayer.com/tools/1point3acres-toolkit/create-collection-task.md
- `create_thread` — Write — https://policylayer.com/tools/1point3acres-toolkit/create-thread.md
- `interviews_export` — Write — https://policylayer.com/tools/1point3acres-toolkit/interviews-export.md
- `save_thread` — Write — https://policylayer.com/tools/1point3acres-toolkit/save-thread.md
- `session_login` — Write — https://policylayer.com/tools/1point3acres-toolkit/session-login.md
- …and 2 more: https://policylayer.com/tools/1point3acres-toolkit.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=1point3acres-toolkit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/1point3acres-toolkit