
Connect Cerbos Access Control to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage authorization and audit permissions using natural language.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 19 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 19 available through Cerbos.
- 01
Get policy
Retrieves a specific policy using its unique ID.
- 02
Get schema
Fetches a specific resource schema by its ID.
- 03
Get authzen config
Returns the configuration metadata for AuthZEN.
- 04
Authzen evaluations
Runs batch access evaluations for AuthZEN.
05-08
4 capabilities in this set.
Part of 19 available through Cerbos.
- 05
Delete policy
Removes a policy from your Cerbos instance by ID.
- 06
Disable policy
Turns off a specific policy without deleting it.
- 07
Enable policy
Reactivates a previously disabled policy.
- 08
Get server info
Provides the current version and build details of your Cerbos instance.
09-12
4 capabilities in this set.
Part of 19 available through Cerbos.
- 09
List audit logs
Retrieves the access logs for auditing and compliance.
- 10
List policies
Returns a list of all currently configured policies.
- 11
List schemas
Shows all resource schemas currently in use.
- 12
Update policy
Modifies the configuration of an existing policy.
13-16
4 capabilities in this set.
Part of 19 available through Cerbos.
- 13
Add policy
Creates a new policy in the system.
- 14
Add schema
Creates or updates a resource schema.
- 15
Authzen evaluation
Performs a single access evaluation for AuthZEN.
- 16
Check resources
Evaluates if specific principals have rights to perform actions on resources.
17-19
3 capabilities in this set.
Part of 19 available through Cerbos.
- 17
Get health
Checks the current health status of your Cerbos instance.
- 18
Get metrics
Fetches Prometheus metrics from your Cerbos setup.
- 19
Plan resources
Generates an AST query plan to help filter resources based on authorization logic.
Real work
What teams actually run
Rapid Policy Testing
A developer needs to verify if a new RBAC rule works as intended before deploying it to production.
Security Auditing
A security engineer needs to quickly pull access logs to investigate a suspicious permission request.
Database Filtering
An engineer uses query plans to ensure database queries only return resources the user is allowed to see.
System Health Checks
An SRE checks the status and Prometheus metrics of the policy engine during a deployment.
Automate a task
Put Cerbos to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
Cerbos works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put Cerbos to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
1011ms average. Fast in production.
Cerbos is checked daily against the live service.
- Fastest day
- 722ms
- Slowest day
- 1480ms
- 14-day trend
- Slowing+25%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 19 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Cerbos, so you can see the experience inside your AI.
It does not authenticate your account with Cerbos. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Cerbos Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_InOwgNCcuNoJDDtlbw3Rpbk72NQ9Y39enLJWWQOg/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Cerbos capabilities are ready to use.
{
"mcpServers": {
"cerbos-access-control-mcp": {
"url": "https://edge.vinkius.com/vk_preview_InOwgNCcuNoJDDtlbw3Rpbk72NQ9Y39enLJWWQOg/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up Cerbos in Claude and other AIs
Who it's for
Built for the work Cerbos owners hand off.
This MCP is built for technical teams managing complex authorization logic who want to move faster.
- 01
Security Engineers
They use the agent to audit policies and verify permission logic without manual API calls.
- 02
Backend Developers
They use the agent to test authorization scenarios and generate database filters during development.
- 03
Compliance Officers
They use the agent to pull audit logs and policy definitions to meet security standards.
FAQ
Questions Cerbos owners ask.
- 01
How do I connect this MCP to my Cerbos instance?
You subscribe to the MCP on Vinkius and then enter your Cerbos PDP URL and any required Admin credentials. Once connected, it is ready to use in your AI client.
- 02
Which AI clients can I use with this MCP?
You can use any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.
- 03
Can I manage my policies through the chat?
Yes, you can use capabilities like add_policy, update_policy, and delete_policy to manage your RBAC and ABAC rules through your agent.
- 04
Is it possible to audit access through the AI?
Yes, you can use the list_audit_logs capability to retrieve access logs for compliance and security reviews.
- 05
Does this MCP support complex query planning?
Yes, the plan_resources capability allows your agent to generate AST query plans for filtering resources based on your authorization logic.
- 06
Can I test if a specific user has access to a resource without writing code?
Yes. You can ask the agent to use the check_resources capability by providing the principal (user) details and the resource you want to check. The agent will return the allowed or denied status based on your Cerbos policies.
- 07
How do I view all the authorization policies currently loaded in my Cerbos server?
Simply ask the agent to 'list all policies'. It will invoke the list_policies capability (requires Admin credentials) and display the IDs of all active policies in your environment.
- 08
Can the AI help me generate filters for my database based on permissions?
Yes, by using the plan_resources capability. The agent will generate a query plan (AST) that describes the conditions under which a user is allowed to access resources, which you can then apply to your database queries.
Explore
More in Developer Tools
Cerbos AI Connector
Decouple authorization logic from your application. Evaluate permissions, generate query plans, and manage acc
ViewPermit.io AI Connector
Orchestrate full-stack authorization, manage RBAC/ReBAC policies, and evaluate permissions in real-time via Pe
ViewLit Protocol (Decentralized Access Control) AI Connector
Manage decentralized access control, Programmable Key Pairs (PKPs), and execute immutable Lit Actions within T
ViewAserto AI Connector
Manage authorization policies and evaluate access control decisions via Aserto — run Rego queries, check user
View
Suggestions
Permify AI Connector
Manage fine-grained authorization and access control via Permify — write schemas, manage relation tuples, and
ViewPermify AI Connector
Manage fine-grained authorization and access control via Permify — write schemas, manage relation tuples, and
ViewCodeRabbit AI Connector
Manage AI-powered code reviews via CodeRabbit — list users, track PR review metrics, audit admin actions, and
ViewAccessibility Prover AI Connector
Accessibility Prover is a pre-build validation system that forces WCAG 2.2 AA compliance before code is writte
View
Connect Cerbos to Claude, Cursor, ChatGPT & more
