AI agents use complete_task to create or update resources in Notion — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Notion environment.
Completing a task updates a task's status field in Notion, which is a data modification that can be undone by marking it incomplete again. This is not destructive (data is not deleted), not financial, not a read-only operation, and not an execute-arbitrary-code action. It falls squarely into the Write category.
From the tool's definition Tool description states 'Mark a task as complete' — this modifies task status in Notion, which is a reversible write operation. The tool name 'complete_task' and description explicitly indicate state change.
Attacks that exploit this kind of access
Mark a task as complete by name or ID. It is categorised as a Write tool in the Notion MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Notion 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 Notion. 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 Notion MCP server (kuldeepjha5176/notion-mcp-server). 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 →