Agent Runtime Security
Check every agent action as it runs
Ferentin decides each tool call an agent makes against policy, at the moment it is made. Routine calls go through, forbidden ones are refused and risky ones wait for a person.
The problem
Access granted once is not enough
An agent signs in once, then makes hundreds of tool calls with nobody watching. Each call can look harmless while the sequence is not: read a customer list, then send it to an outside service. The decision has to happen at every call, not at login.
How it works
How it works
- 1
Write the rule per tool
An MCP policy names the servers, the people it applies to and an effect for each tool: Allow, Deny or Step-up. Read-only tools can run freely while updates wait for an approver and deletes are refused. Every call is checked against the policy when it is made.
- 2
Hold risky actions for a person
A Step-up rule pauses the call and raises an approval request with the tool, its arguments and the person who asked. An approver decides in Slack or in the Inbox. Nobody can approve their own request. If no one decides in time, the action is refused.
- 3
Treat tool output as data
Tool results are where injected instructions hide. Ferentin can datamark and wrap each result so the model reads it as data. It can also strip the invisible Unicode attackers use to hide instructions. Arguments are checked against the tool’s input schema before the call is forwarded.
- 4
See what agents actually did
Intent Flow draws every request in a window, from the person or Slack channel through the agent and provider to the tool and the destination it reached. A flow you did not expect is an incident. Open any node’s calls in Activity, where every row carries its policy decision.
Works with your stack
Works with your stack
Policy applies to the agents your teams already use and to the MCP servers they call.
Agent runtime security means deciding each action an AI agent takes at the moment it takes it, not only when it signs in. Ferentin evaluates every tool call an agent makes over MCP against policy: who is asking, through which agent, on which server and with which tool. The call is allowed, refused or held for a human approver. The decision is recorded on the audit trail.
Go deeper
Learn more
- The CISO Reference for Agentic AISeven control families for agentic AI, including per-call approval and where the families meet.
- OWASP Agentic Top 10 coverageHow Ferentin maps to each risk for agentic applications, gaps included.
- Ferentin for Slack demoWatch a privileged action pause for approval in a Slack channel.
Related
- MCP SecurityDecide which agents reach which MCP servers and tools, and inspect every call.
- Ferentin for SlackA governed AI agent in Slack, with approvals and an audit trail.
- AI Data Loss PreventionRedact or block secrets and personal data in prompts, tool calls and results.
- AI ComplianceSigned evidence of every AI call, policy decision and approval.
See it on your own stack
Walk through it with our team on your identity provider, your models and your MCP servers. Or start free today.