14 tools. 10 can modify or destroy data without limits.
3 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (GOOGLETASKS_CLEAR_TASKS, GOOGLETASKS_DELETE_TASK, GOOGLETASKS_DELETE_TASK_LIST) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (GOOGLETASKS_CREATE_TASK_LIST, GOOGLETASKS_INSERT_TASK, GOOGLETASKS_MOVE_TASK) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
GOOGLETASKS_CLEAR_TASKS:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
GOOGLETASKS_CREATE_TASK_LIST:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
GOOGLETASKS_GET_TASK:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Google Tasks server exposes 3 destructive tools including GOOGLETASKS_CLEAR_TASKS, GOOGLETASKS_DELETE_TASK, GOOGLETASKS_DELETE_TASK_LIST. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Google Tasks server has 7 write tools including GOOGLETASKS_CREATE_TASK_LIST, GOOGLETASKS_INSERT_TASK, GOOGLETASKS_MOVE_TASK. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.
14 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 10 can modify, create, or delete data.
One line change. Instead of running the Google Tasks server directly, prefix it with Intercept: intercept -c google-tasks.yaml -- npx -y @@overlay-one/google-tasks-mcp-server. Download a pre-built policy from policylayer.com/policies/google-tasks and adjust the limits to match your use case.
Starter policies available for each. Same risk classification, same one-command setup.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.