start_task · Keshro MCP: Risk & Policy

WHAT IT DOES

What start_task does on Keshro MCP

AI agents invoke start_task to trigger actions in Keshro MCP. 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.

WHY IT NEEDS A POLICY

Why start_task needs a policy

Despite the empty description, the name 'start_task' in the context of a high-stakes engineering execution layer suggests the tool initiates execution or triggers a task. This constitutes an Execute action because it likely runs or launches code/operations whose effects depend on what the task contains.

From the tool's definition Tool named 'start_task' with empty description on an 'intelligent execution layer for coding agents' server that 'enables AI agents to manage plans, tasks, and integrations.' Sibling tools (complete_task, block_task, edit_task) suggest task state mutations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_task Rate-limited

start_task stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_task": {
      "limits": [
        {
          "counter": "start_task_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Keshro MCP, so you can run agents against it safely.

FAQ

Questions about start_task

What does the start_task tool do? +

start_task. It is categorised as a Execute tool in the Keshro MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on start_task? +

Register the Keshro MCP server in PolicyLayer and add a rule for start_task: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Keshro MCP. Nothing to install.

What risk level is start_task? +

start_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_task? +

Yes. Add a rate_limit block to the start_task rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block start_task completely? +

Set action: deny in the PolicyLayer policy for start_task. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides start_task? +

start_task is provided by the Keshro MCP server (jlewitt1/keshro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.