annotate_worker

THE RISK

Low Risk

Why annotate_worker needs a policy

With no description available, we can only infer from the name. 'Annotate' typically implies adding metadata or labels, which would be a Write operation at most. However, given the extremely low confidence due to empty description, and that annotations are generally low-risk reversible metadata changes, this is categorized conservatively.

From the tool's definition Tool description is empty and uninformative; tool name 'annotate_worker' only suggests adding annotations/labels to a worker session.

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

POLICY

How to control annotate_worker

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "annotate_worker": {
      "limits": [
        {
          "counter": "annotate_worker_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

annotate_worker gets a rate cap, and everything else on the server is denied unless you say otherwise.

Create a free account and register Claude Team MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

SET A RULE FOR THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Claude Team MCP Server tools

Destructive prune_recovered_workers prune_recovered_workers Destructive close_workers close_workers Execute wait_idle_workers wait_idle_workers Execute message_workers message_workers Execute spawn_workers spawn_workers Other adopt_worker adopt_worker Read check_idle_workers check_idle_workers Read discover_workers discover_workers

All 16 Claude Team MCP Server tools →

Other tools on other servers

Android Forensics ADB MCP Server generate_app_analysis_report Ethereum Tools add Math MCP Server complex_analysis_suite Crypto_MCP aes_encrypt

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Tool risk categories → How PolicyLayer classifies MCP tools by what they can do.
MCP tool → What an MCP tool is and how clients discover and call it.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about annotate_worker

What does the annotate_worker tool do? +

annotate_worker. It is categorised as a Other tool in the Claude Team MCP Server MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on annotate_worker? +

Register the Claude Team MCP Server MCP server in PolicyLayer and add a rule for annotate_worker: 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 Claude Team MCP Server. Nothing to install.

What risk level is annotate_worker? +

annotate_worker is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit annotate_worker? +

Yes. Add a rate_limit block to the annotate_worker 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 annotate_worker completely? +

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

annotate_worker is provided by the Claude Team MCP Server MCP server (martian-engineering/maniple). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Claude Team MCP Server tool call.

Start from Claude Team MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →