Mark a task as completed
AI agents use complete_task to create or update resources in Calendar Mcp — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Calendar Mcp environment.
This tool changes task state from incomplete to complete, which is a modification of data. It is reversible (a completed task can be marked incomplete again), so it falls under Write rather than Destructive. The severity is medium because misuse could corrupt calendar workflows or task tracking, but the impact is limited to task metadata and can be undone.
From the tool's definition Tool description states 'Mark a task as completed', which modifies the state of a task object (reversible status change). The server description confirms this is part of CRUD operations on calendar/task management.
Attacks that exploit this kind of access
Mark a task as completed. It is categorised as a Write tool in the Calendar Mcp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Calendar 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 Calendar Mcp. 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 Calendar MCP server (ydrogen/calendar-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 →