start_a_task · Interview MCP: Risk & Policy

WHAT IT DOES

What start_a_task does on Interview

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

WHY IT NEEDS A POLICY

Why start_a_task needs a policy

Starting a task changes its state (likely from pending to in-progress), which is a reversible status modification. This is a Write operation. It does not delete, execute code, or involve finances. Severity is medium because misuse could alter task states across lists, but effects are reversible.

From the tool's definition Comenzar, empezar o start una tarea / task — starts/begins a task, which modifies its status

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_a_task Rate-limited

start_a_task stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_a_task": {
      "limits": [
        {
          "counter": "start_a_task_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about start_a_task

What does the start_a_task tool do? +

Comenzar, empezar o start una tarea / task con nombre 'name' en la lista llamada 'listname'. It is categorised as a Write tool in the Interview MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on start_a_task? +

Register the Interview MCP server in PolicyLayer and add a rule for start_a_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 Interview. Nothing to install.

What risk level is start_a_task? +

start_a_task is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit start_a_task? +

Yes. Add a rate_limit block to the start_a_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_a_task completely? +

Set action: deny in the PolicyLayer policy for start_a_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_a_task? +

start_a_task is provided by the Interview MCP server (matilarrazabal/mcp-server-interview). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.