Medium Risk

add_task

add_task

How to control add_task ↓

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

Medium Risk

The tool creates/adds data (a task) reversibly—tasks can be modified or deleted via sibling tools. This fits the Write category. Severity is medium because an agent could create arbitrary or malicious tasks, potentially causing workflow disruption or misuse of the task system, but the impact is contained to task records without system-level or financial consequences.

From the tool's definition Tool named 'add_task' with no description provided. Sibling tools include 'complete_task', 'get_task', 'list_tasks', and 'remove_task', indicating a task management system. The naming convention strongly suggests this creates or adds new task records.

Documented attack patterns abuse exactly the kind of access add_task gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Starter for Puch AI, and nothing reaches the server without passing your rules. This is the rule we recommend for add_task:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "add_task": {
      "limits": [
        {
          "counter": "add_task_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add_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.

  1. Create a free account and register MCP Starter for Puch AI — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the add_task tool do? +

add_task. It is categorised as a Write tool in the MCP Starter for Puch AI MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_task? +

Register the MCP Starter for Puch AI MCP server in PolicyLayer and add a rule for add_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 MCP Starter for Puch AI. Nothing to install.

What risk level is add_task? +

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

Can I rate-limit add_task? +

Yes. Add a rate_limit block to the add_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 add_task completely? +

Set action: deny in the PolicyLayer policy for add_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 add_task? +

add_task is provided by the MCP Starter for Puch AI MCP server (turboml-inc/mcp-starter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Starter for Puch AI tool call.

Deterministic rules across all 12 MCP Starter for Puch AI tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

12 MCP Starter for Puch AI tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.