35 tools. 27 can modify or destroy data without limits.
2 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (ae_delete_layer, ae_remove_effect) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (ae_add_audio_markers, ae_add_expression, ae_add_keyframe) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (ae_animate_property, mcp_performance_metrics) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
ae_delete_layer:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
ae_add_audio_markers:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
ae_check_connection:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Ae server exposes 2 destructive tools including ae_delete_layer, ae_remove_effect. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Ae server has 23 write tools including ae_add_audio_markers, ae_add_expression, ae_add_keyframe. 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.
35 tools across 4 categories: Destructive, Execute, Read, Write. 8 are read-only. 27 can modify, create, or delete data.
One line change. Instead of running the Ae server directly, prefix it with Intercept: intercept -c ae.yaml -- npx -y @ae-mcp-server. Download a pre-built policy from policylayer.com/policies/ae 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.