4,000+ servers built on vurb.ts
Vinkius
Cerbos

Cerbos MCP Server with 6 Tools for Claude, Cursor, and AI Agents

MCP Inspector GDPR Free for Subscribers

Decouple authorization logic from your application. Evaluate permissions, generate query plans, and manage access control via AI. Vinkius routes your AI agents directly to Cerbos through a governed connection. 6 tools ready to use with Claude, ChatGPT, Cursor, or any AI agent — no hosting, no setup, connect in 30 seconds.

Built for AI Agents by Vinkius

Compatible with every major AI agent and IDE

ClaudeClaude
ChatGPTChatGPT
CursorCursor
GeminiGemini
WindsurfWindsurf
VS CodeVS Code
JetBrainsJetBrains
VercelVercel
+ other MCP clients
AI AgentVinkius
High Security·Kill Switch·Plug and Play
Cerbos
Fully ManagedVinkius Servers
60%Token savings
High SecurityEnterprise-grade
IAMAccess control
EU AI ActCompliant
DLPData protection
V8 IsolateSandboxed
Ed25519Audit chain
<40msKill switch
Stream every event to Splunk, Datadog, or your own webhook in real-time

* 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

What is the Cerbos MCP Server?

The Cerbos MCP Server routes AI agents like Claude, ChatGPT, and Cursor directly to Cerbos via 6 tools. Decouple authorization logic from your application. Evaluate permissions, generate query plans, and manage access control via AI. Powered by Vinkius — your credentials stay on your side of the connection, every request is auditable. Connect in under 2 minutes.

Built-in capabilities (6)

authzen_evaluationauthzen_evaluationscheck_resourcesget_authzen_configget_server_infoplan_resources

Tools for your AI Agents to operate Cerbos

Ask your AI agent "Check if principal 'user_123' with role 'editor' can 'edit' resource 'document:abc'." and get the answer without opening a single dashboard. With 6 tools connected to real Cerbos data, your agents reason over live information, cross-reference it with other MCP servers, and deliver insights you would spend hours assembling manually.

Works with Claude, ChatGPT, Cursor, and any MCP-compatible client. Powered by Vinkius — your credentials never touch the AI model, every request is auditable. Connect in under two minutes.

Why teams choose Vinkius

One subscription gives you the infrastructure to connect your AI agents to thousands of MCP servers — and deploy your own to the Vinkius Edge. Your credentials stay yours. Your data flows directly between your agent and the API. DLP blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade routing and governance, zero maintenance.

Build your own MCP Server with our secure development framework →

The Cerbos App Connector works with every AI agent you already use

…and any MCP-compatible client

CursorClaudeOpenAIVS CodeCopilotGoogleLovableMistralAWSCursorClaudeOpenAIVS CodeCopilotGoogleLovableMistralAWS

Use all 6 Cerbos tools with your AI agents right now

Vinkius routes your AI agents to Cerbos through a governed proxy. Beyond a simple connection, you get full visibility into every action your agents perform, with enterprise-grade security and up to 60% savings on AI costs.

Explore Tools Hub
authzen

Authzen evaluation on Cerbos

Single action evaluation using the AuthZEN entity model

authzen

Authzen evaluations on Cerbos

Supports execute_all, deny_on_first_deny, and permit_on_first_permit semantics. Batch evaluation of multiple access requests using AuthZEN

check

Check resources on Cerbos

This is a read-only evaluation. Evaluates permissions for a principal on a set of resources

get

Get authzen config on Cerbos

Returns endpoint URLs for the AuthZEN APIs

get

Get server info on Cerbos

Returns the version and build details of the Cerbos instance

plan

Plan resources on Cerbos

Produces a query plan for obtaining a list of resources a principal is allowed to access

What the Cerbos MCP Server unlocks

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_resources to instantly verify if a principal can perform specific actions on resources based on your policies.
  • Query Planning — Generate AST-based query plans with plan_resources to filter database results according to user permissions.
  • AuthZEN Compliance — Leverage standardized access requests using authzen_evaluation and authzen_evaluations tools.
  • System Monitoring — Check instance health and build metadata using get_server_info and get_authzen_config.

How it works

1. Subscribe to this server
2. Provide your Cerbos instance base URL (e.g., http://localhost:3592)
3. 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

Frequently asked questions about the Cerbos MCP Server

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.

Vinkius AI Gateway

We built the connector to Cerbos. Now put your agents to work. Fully governed.

Vinkius is the AI Gateway with managed hosting. Stop building connectors. Every connection runs inside eight layers of security.

How it works
Infrastructure

Hosted, sandboxed, and live on AWS. You don't provision anything. You don't maintain anything. You connect.

Visibility

Every tool call, every token, every response. Logged and auditable. Data flows direct from Cerbos to your agent. Nothing is stored on our side. Ever.

Control

Eight governance layers on every request. Sensitive data redacted before it reaches the model. Kill switch if anything goes sideways. Always on.