Update an existing task. Only provided fields are changed.
AI agents use update-task to create or update resources in Google Tasks — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google Tasks environment.
The tool modifies existing task data (update operation), which is a Write action. It is not Destructive because updates are reversible—the original data can be restored by updating again with previous values. It is not Read (no data retrieval), Execute (no code/command execution), Financial (no money movement), or Other.
From the tool's definition Tool name is 'update-task' and description states 'Update an existing task. Only provided fields are changed.' This is a reversible modification operation on task data.
Attacks that exploit this kind of access
Update an existing task. Only provided fields are changed. It is categorised as a Write tool in the Google Tasks MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google Tasks MCP server in PolicyLayer and add a rule for update-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 Google Tasks. Nothing to install.
update-task 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 update-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.
Set action: deny in the PolicyLayer policy for update-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.
update-task is provided by the Google Tasks MCP server (scottie-will/google-tasks-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 →