109 tools. 55 can modify or destroy data without limits.
12 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (gog_calendar_delete, gog_classroom_announcements_delete, gog_classroom_courses_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (gog_auth_add, gog_calendar_create, gog_calendar_update) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (gog_auth_run, gog_calendar_run, gog_classroom_run) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
gog_calendar_delete:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
gog_auth_add:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
gog_auth_list:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Gogcli server exposes 12 destructive tools including gog_calendar_delete, gog_classroom_announcements_delete, gog_classroom_courses_delete. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Gogcli server has 34 write tools including gog_auth_add, gog_calendar_create, gog_calendar_update. 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.
109 tools across 4 categories: Destructive, Execute, Read, Write. 54 are read-only. 55 can modify, create, or delete data.
One line change. Instead of running the Gogcli server directly, prefix it with Intercept: intercept -c gogcli.yaml -- npx -y @gogcli-mcp. Download a pre-built policy from policylayer.com/policies/gogcli 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.