# startTask

Start a task (change status to in_progress)\n\n

Agent View of the PolicyLayer registry record for `startTask`. HTML page: https://policylayer.com/tools/108yen-task-orchestrator-mcp/starttask

## Facts

- Tool: `startTask`
- Server: Task Orchestrator (`108yen/task-orchestrator-mcp`) — https://policylayer.com/tools/108yen-task-orchestrator-mcp.md
- Homepage: https://github.com/108yen/task-orchestrator-mcp
- Risk category: Write (Medium 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": "startTask",
    "arguments": {}
  }
}
```

## Why startTask is rated Medium

This tool updates a task's status to 'in_progress', which is a reversible state change (a write/update operation). It does not delete data, execute code, or involve financial transactions. The severity is medium because misuse could disrupt task orchestration workflows by incorrectly marking tasks as started.

From the tool's own definition: "'Start a task (change status to in_progress)' — the tool modifies the status field of an existing task record"

## Use case

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

## Recommended policy (PolicyLayer)

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

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

## Other tools on Task Orchestrator (6)

- `deleteTask` — Destructive — https://policylayer.com/tools/108yen-task-orchestrator-mcp/deletetask.md
- `getTask` — Read — https://policylayer.com/tools/108yen-task-orchestrator-mcp/gettask.md
- `listTasks` — Read — https://policylayer.com/tools/108yen-task-orchestrator-mcp/listtasks.md
- `completeTask` — Write — https://policylayer.com/tools/108yen-task-orchestrator-mcp/completetask.md
- `createTask` — Write — https://policylayer.com/tools/108yen-task-orchestrator-mcp/createtask.md
- `updateTask` — Write — https://policylayer.com/tools/108yen-task-orchestrator-mcp/updatetask.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=108yen-task-orchestrator-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/108yen-task-orchestrator-mcp