Patch a task's fields. status='completed' completes it (or use task_complete).
AI agents use task_update to create or update resources in Google Workspace — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Workspace environment.
This tool modifies existing task data (status and other fields) but does not delete or destroy information—changes are reversible by updating the task again. It is not Execute because it does not run arbitrary code or commands; it operates within a structured task-update API. It is not Destructive because patching task fields is not irreversible.
From the tool's definition Tool description explicitly states it can 'Patch a task's fields' and mentions updating task status, including completion.
Attacks that exploit this kind of access
Patch a task's fields. status='completed' completes it (or use task_complete). It is categorised as a Write tool in the Google Workspace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Workspace MCP server in PolicyLayer and add a rule for task_update: 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 Google Workspace. Nothing to install.
task_update is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the task_update 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.
Set action: deny in the PolicyLayer policy for task_update. 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.
task_update is provided by the Google Workspace MCP server (rajool/google-workspace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →