314 tools. 208 can modify or destroy data without limits.
41 destructive tools with no built-in limits. Policy required.
Last updated:
Destructive tools (cancelActionWithId, changePasswordWithId, deleteAPIKeyWithId) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.
Write operations (actionUserWithId, activateReactorWithId, commentOnUserWithId) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.
Execute tools (startIdentityProviderLoginWithId, startPasswordlessLoginWithId, startTwoFactorLoginWithId) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.
cancelActionWithId:
rules:
- action: deny Destructive tools should never be available to autonomous agents without human approval.
actionUserWithId:
rules:
- rate_limit: 30/hour Prevents bulk unintended modifications from agents caught in loops.
retrieveActionWithId:
rules:
- rate_limit: 60/minute Controls API costs and prevents retry loops from exhausting upstream rate limits.
Yes. The Mcp Api server exposes 41 destructive tools including cancelActionWithId, changePasswordWithId, deleteAPIKeyWithId. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.
The Mcp Api server has 161 write tools including actionUserWithId, activateReactorWithId, commentOnUserWithId. 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.
314 tools across 4 categories: Destructive, Execute, Read, Write. 106 are read-only. 208 can modify, create, or delete data.
One line change. Instead of running the Mcp Api server directly, prefix it with Intercept: intercept -c io-fusionauth-mcp-api.yaml -- npx -y @@fusionauth/mcp-api. Download a pre-built policy from policylayer.com/policies/io-fusionauth-mcp-api 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.