Authorize Semantic Kernel function calls with Cerbos
Enforce policy-driven authorization on Semantic Kernel plugin and function invocations using Cerbos.
Function authorization
Control which Semantic Kernel plugins and functions each user or role can invoke with fine-grained Cerbos policies
Context-aware decisions
Authorize function calls based on user identity, roles, attributes, and request context at runtime
Audit every function call
Every authorization decision is logged with full context, giving you a complete audit trail of AI agent behavior
How Cerbos works with Semantic Kernel
AI agents and tools introduce a new class of authorization challenges. They act on behalf of users, access sensitive data, and chain operations, all of which need fine-grained access control.
Cerbos provides policy-driven authorization that controls what AI systems can do, which data they can access, and on whose behalf. Policies are written in human-readable YAML and evaluated at request time.
With Cerbos and Semantic Kernel, you get guardrails that scale with your AI adoption, centrally managed policies, full audit trails, and sub-millisecond decision times that don't slow down agent workflows.
How Cerbos authorizes Semantic Kernel functions
- Define policies for plugin and function access, Write YAML policies that specify which plugins and functions each user or role can invoke based on identity, attributes, and context.
- Application requests authorization before each function call, Before invoking a plugin function, the application sends the user context, function name, and target resource to the Cerbos PDP.
- Cerbos evaluates the request against policies, The PDP applies fine-grained rules considering the user's identity, role, and any additional attributes you provide.
- Function call proceeds or is blocked, Cerbos returns an allow or deny decision. The application enforces it, with every decision logged for audit.
FAQ
How does Cerbos authorize Semantic Kernel function calls?
Before a Semantic Kernel agent invokes a plugin function, the application sends the user context, function name, and target resource to the Cerbos PDP. Cerbos evaluates fine-grained policies and returns an allow or deny decision.
Can I restrict plugin access per user or role?
Yes. Cerbos policies are attribute-based, so you can restrict plugin and function access by role, department, tenant, or any other context you provide. Policies are written in YAML and managed outside your application code.
Which Semantic Kernel languages does this work with?
Cerbos provides SDKs for .NET, Python, and Java, matching Semantic Kernel's supported languages. Authorization is evaluated via the Cerbos PDP API, so it works with any Semantic Kernel runtime.
Learn more about Cerbos
Related integrations
View all integrations →
Cerbos + Semantic Kernel
- Cerbos policies govern AI agent tool access and data visibility
- Full audit trail for every AI tool call and data access
- Per-user permissions enforced across autonomous agent workflows
- Sub-millisecond policy evaluation with no agent pipeline overhead
Authorization for AI systems
By industry
By business requirement
Useful links
What is Cerbos?
Cerbos is an end-to-end enterprise authorization software for Zero Trust environments and AI-powered systems. It enforces fine-grained, contextual, and continuous authorization across apps, APIs, AI agents, MCP servers, services, and workloads.
Cerbos consists of an open-source Policy Decision Point, Enforcement Point integrations, and a centrally managed Policy Administration Plane (Cerbos Hub) that coordinates unified policy-based authorization across your architecture. Enforce least privilege & maintain full visibility into access decisions with Cerbos authorization.