622 tools. 337 can modify or destroy data without limits.
105 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (campaign_bulk_delete_catalog_ad_items, cancel_signature_request, delete_advertiser) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (add_user_list_attribute_values, archive_advertiser, archive_campaign) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
campaign_bulk_delete_catalog_ad_items:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
add_user_list_attribute_values:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
call_adbutler_api:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The AdButler server exposes 105 destructive tools including campaign_bulk_delete_catalog_ad_items, cancel_signature_request, delete_advertiser. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The AdButler server has 232 write tools including add_user_list_attribute_values, archive_advertiser, archive_campaign. 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.
622 tools across 3 categories: Destructive, Read, Write. 285 are read-only. 337 can modify, create, or delete data.
One line change. Instead of running the AdButler server directly, prefix it with Intercept: intercept -c adbutler.yaml -- npx -y @@adbutler/mcp-server. Download a pre-built policy from policylayer.com/policies/adbutler 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.