queue_reading · Gcal MCP: Risk & Policy

WHAT IT DOES

What queue_reading does on Gcal

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

WHY IT NEEDS A POLICY

Why queue_reading needs a policy

This tool creates or stores new entries (articles/URLs) in a reading queue data structure. It is a Write operation because it modifies state by adding new data reversibly—items can be removed or modified later without permanent loss. It has minimal blast radius: a misused agent might add irrelevant URLs, but the queue can be cleared or curated.

From the tool's definition Tool description explicitly states 'Add an article or URL to the reading queue' and 'Articles are saved locally', indicating creation of data records in a reading queue.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

queue_reading Rate-limited

queue_reading 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": {
    "queue_reading": {
      "limits": [
        {
          "counter": "queue_reading_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 Gcal, so you can run agents against it safely.

FAQ

Questions about queue_reading

What does the queue_reading tool do? +

Add an article or URL to the reading queue. Articles are saved locally and can be batch-scheduled into reading time slots later with schedule_readings. It is categorised as a Write tool in the Gcal MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on queue_reading? +

Register the Gcal MCP server in PolicyLayer and add a rule for queue_reading: 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 Gcal. Nothing to install.

What risk level is queue_reading? +

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

Can I rate-limit queue_reading? +

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

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

queue_reading is provided by the Gcal MCP server (kwikkid/gcalcli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.