MCP Gateway
A governed checkpoint every tool connection passes through (authenticated, policy-checked, and logged) so credentials stay central and unapproved servers can't connect.
Part of the Agent Control Fabric: Highflame's identity, policy, and enforcement substrate for AI agents.
Keep exploring the glossary.
Mission drift
When a non-deterministic agent gradually diverges from its intended task. Tracked at runtime so it can be contained before consequences land.
Read →Non-human identity (NHI)
Identities belonging to machines, services, and agents rather than people. Agents are the fastest-growing and least-governed class of NHI.
Read →On-behalf-of (OBO) chain
The unbroken provenance recorded on a credential (who authorized the action, what scope was granted, and how deep the delegation goes) so an audit walks back to a human.
Read →Prompt injection
An attack that manipulates an agent through crafted input (in a prompt, a tool result, or retrieved content) to make it act against policy.
Read →Red teaming
Continuous adversarial testing of AI systems (jailbreaks, extraction, manipulation) with findings turned into enforcement policy and re-scanned to prove the fix.
Read →RFC 8693 (token exchange)
The standard that lets one token be exchanged for another with attenuated scope: the basis for verifiable agent-to-agent delegation.
Read →