Bring Authorization
to OpenAI Agents SDK
Learn how to connect Cerbos to OpenAI Agents SDK and start using 6 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Cerbos MCP Server?
Connect your Cerbos instance to any AI agent to manage complex authorization policies through natural language conversation.
What you can do
- Permission Evaluation — Use
check_resourcesto instantly verify if a principal can perform specific actions on resources based on your policies. - Query Planning — Generate AST-based query plans with
plan_resourcesto filter database results according to user permissions. - AuthZEN Compliance — Leverage standardized access requests using
authzen_evaluationandauthzen_evaluationstools. - System Monitoring — Check instance health and build metadata using
get_server_infoandget_authzen_config.
How it works
- Subscribe to this server
- Provide your Cerbos instance base URL (e.g.,
http://localhost:3592) - Start auditing and testing your access control logic directly from your chat interface
Who is this for?
- Software Engineers — debug complex RBAC/ABAC policies without manual API calls
- Security Auditors — verify permission logic across different roles and resource attributes
- DevOps Teams — monitor Cerbos instance metadata and configuration status
Built-in capabilities (6)
Single action evaluation using the AuthZEN entity model
Supports execute_all, deny_on_first_deny, and permit_on_first_permit semantics. Batch evaluation of multiple access requests using AuthZEN
This is a read-only evaluation. Evaluates permissions for a principal on a set of resources
Returns endpoint URLs for the AuthZEN APIs
Returns the version and build details of the Cerbos instance
Produces a query plan for obtaining a list of resources a principal is allowed to access
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 6 tools from Cerbos through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Cerbos, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Cerbos in OpenAI Agents SDK
Cerbos and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Cerbos to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Cerbos in OpenAI Agents SDK
The Cerbos MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Cerbos for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Cerbos MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I check if a specific user has permission to access a resource?
Yes. Use the check_resources tool by providing the principal (user) details and the resource information. The agent will return an evaluation of allowed or denied actions.
How do I generate a filter for my database based on user permissions?
Use the plan_resources tool. It produces a query plan (AST) that you can use to construct database queries, ensuring users only see records they are authorized to access.
Is it possible to verify the Cerbos server version via AI?
Yes, the get_server_info tool retrieves the version, build date, and commit hash of your connected Cerbos instance.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
SmartChatAI
12 toolsManage AI bots, knowledge bases, and messaging on SmartChatAI with AI agents.
vCita
12 toolsRun your small business with online scheduling, payment collection, and client management that keeps everything in one place.
OpenSearch Vector
6 toolsRun k-NN vector searches on OpenSearch — create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.
HashiCorp Vault
50 toolsSecurely manage secrets, tokens, and encryption keys via HashiCorp Vault — read KV secrets, generate dynamic credentials, and monitor system health.