AI agents use complete_task_tool to create or update resources in Apps Script MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Apps Script MCP environment.
The tool updates an existing task record to mark it as completed, which is a reversible write operation. The task can be unmarked or the completion status changed back, so it does not qualify as Destructive. It does not execute code, read-only retrieve data, move money, or fall into other categories.
From the tool's definition "Mark a task as completed in Google Tasks" — this is a state-change operation that modifies (updates) a task's completion status.
Documented attack patterns abuse exactly the kind of access complete_task_tool gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Apps Script MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for complete_task_tool:
{
"version": "1",
"default": "deny",
"tools": {
"complete_task_tool": {
"limits": [
{
"counter": "complete_task_tool_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}complete_task_tool stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Mark a task as completed in Google Tasks. It is categorised as a Write tool in the Apps Script MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Apps Script MCP server in PolicyLayer and add a rule for complete_task_tool: 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 Apps Script MCP. Nothing to install.
complete_task_tool 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_tool 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_tool. 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_tool is provided by the Apps Script MCP server (sam-ent/google-automation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Apps Script MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
60 Apps Script MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.