Mark a task as completed.
AI agents use complete-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.
Completing a task changes its state but does not delete or destroy data, nor does it execute code or move money. It is a reversible modification of task metadata, fitting the Write category. Severity is low because the blast radius is confined to a single user's task list with no cascade effects or external consequences.
From the tool's definition Tool description states 'Mark a task as completed' — this modifies the status field of an existing task record. The action is reversible (a completed task can be marked incomplete via update-task).
Attacks that exploit this kind of access
Mark a task as completed. 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 complete-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.
complete-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 complete-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 complete-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.
complete-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 →