Policy Violation Blocked
BLOCK- Actor
- MCP-connected assistant
- Human
- Enterprise operator
- Action
- delete_database
- Resource
- Sensitive production resource
- Policy
- Autonomous actor policy boundary
Back to Home
MCP / Tool-Using Agents
Tool access is authority. Govern it explicitly.
The question is not whether an MCP server is trusted. The question is whether this actor may invoke this operation now.
Core problem
Tool invocation expands agent authority quickly. Runtime controls define allowed operations per tool and per actor context.
Typical actors
- MCP-connected assistants
- Internal tool-calling agents
- Task automation copilots
Allowed
- read_customer
- search_documents
- create_ticket
- query_status
Blocked
- delete_database
- bulk_export_secrets
- disable_monitoring
- unapproved admin operations
Publish only capabilities that are technically supported in your deployment.
Run a Pilot