Frequently Asked Questions
Start with Kontext basics, then jump into authorization guides for AI agents.
Kontext Basics
What Kontext is, where it sits, and which teams use it.
- What is Kontext?
- Kontext is runtime authorization infrastructure for AI agents. It evaluates sensitive tool, API, MCP, and credential requests at execution time, issues scoped short-lived credentials, and records policy decisions for audit.
- Who is Kontext built for?
- Kontext is built for security, platform, AI engineering, and developer-experience teams deploying coding agents, MCP servers, browser agents, internal copilots, and autonomous workflows that touch real data or production systems.
- Does Kontext replace IAM, OAuth, or SSO?
- No. Kontext sits next to existing identity systems. IAM, OAuth, and SSO establish identity and broad authorization. Kontext decides whether a specific agent action should be allowed now, under the current user, session, tool, resource, parameters, and policy.
- Can Kontext run locally?
- Yes. Kontext Guard runs locally for Claude Code guardrails, tool-call traces, and risk visibility. Hosted Kontext adds team policy, scoped credentials, organization controls, and shared audit trails.
Guides
Authorization
How agents should be authorized before they use tools, APIs, and credentials.