180 tools. 79 can modify or destroy data without limits.
21 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (arcane_apikey_delete, arcane_container_delete, arcane_environment_delete) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (arcane_apikey_create, arcane_auth_login, arcane_container_create) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (arcane_build_get, arcane_build_image, arcane_build_list) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
arcane_apikey_delete:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
arcane_apikey_create:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
arcane_apikey_list:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Arcane server exposes 21 destructive tools including arcane_apikey_delete, arcane_container_delete, arcane_environment_delete. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Arcane server has 39 write tools including arcane_apikey_create, arcane_auth_login, arcane_container_create. 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.
180 tools across 4 categories: Destructive, Execute, Read, Write. 101 are read-only. 79 can modify, create, or delete data.
One line change. Instead of running the Arcane server directly, prefix it with Intercept: intercept -c arcane.yaml -- npx -y @@randomsynergy/arcane-mcp-server. Download a pre-built policy from policylayer.com/policies/arcane 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.