add_task_reference · Agentic Task System MCP: Risk & Policy

WHAT IT DOES

What add_task_reference does on Agentic Task System

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

WHY IT NEEDS A POLICY

Why add_task_reference needs a policy

This tool creates or modifies task data reversibly by appending resource references (URLs or notes) to a task. It does not delete, execute code, move money, or trigger external operations—it simply adds metadata to an existing task. This is a classic Write operation with low severity since the blast radius of adding incorrect references is minimal and easily corrected.

From the tool's definition Tool name 'add_task_reference' and description explicitly states 'WRITE. Adds a resource' indicating it modifies task data by adding references/URLs.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_task_reference Rate-limited

add_task_reference 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": {
    "add_task_reference": {
      "limits": [
        {
          "counter": "add_task_reference_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 Agentic Task System, so you can run agents against it safely.

FAQ

Questions about add_task_reference

What does the add_task_reference tool do? +

WRITE. Adds a resource the task consults (an external URL or a reference note) to its. It is categorised as a Write tool in the Agentic Task System 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_reference? +

Register the Agentic Task System MCP server in PolicyLayer and add a rule for add_task_reference: 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 Agentic Task System. Nothing to install.

What risk level is add_task_reference? +

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

Can I rate-limit add_task_reference? +

Yes. Add a rate_limit block to the add_task_reference 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_reference completely? +

Set action: deny in the PolicyLayer policy for add_task_reference. 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_reference? +

add_task_reference is provided by the Agentic Task System MCP server (renezander030/agentic-task-system). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.