Cerbos Connector for AI agents.
6 live capabilities
Manage granular permissions and access control policies through natural language.
Waiting for input…
Why people use Cerbos
Cerbos Authorization Policy Auditing for Security Teams
This Connector changes that by letting you talk to your Cerbos instance directly. You can ask your agent to verify a permission or audit a batch of requests, getting a clear answer in seconds instead of minutes of manual work.
What Vinkius changes
That you get instant, conversational access to your authorization logic without manual testing.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Debugging a Permission Denied error
A developer asks the agent to check why a specific user can't edit a document using check_resources.
- Real-world use case 02
Building a secure admin dashboard
A developer uses plan_resources to see which filters to apply to a list of users to keep it secure.
- Real-world use case 03
Security auditing
An auditor asks the agent to evaluate a batch of requests to find potential security gaps using authzen_evaluations.
Complete set · 6capabilities
The complete Cerbos capability set.
These are the exact actions your AI can choose when you ask it to work with Cerbos.
01—03
3 capabilities in this set.
Part of 6 available through Cerbos.
- 01 Capability
Get server info
Get the current version and build details of your Cerbos instance. This is useful for verifying your current deployment status.
- 02 Capability
Get authzen config
Retrieve the endpoint URLs for your AuthZEN APIs. This helps you quickly grab the configuration needed for your integration.
- 03 Capability
Authzen evaluation
Perform a single action evaluation using the AuthZEN entity model. Use this for one-off permission checks.
04—06
3 capabilities in this set.
Part of 6 available through Cerbos.
- 04 Capability
Authzen evaluations
Batch evaluate multiple access requests using AuthZEN semantics like deny_on_first_deny. This helps you check many permissions at once.
- 05 Capability
Check resources
Verify if a specific principal has permission to perform actions on a set of resources. Use this for quick, read-only permission checks.
- 06 Capability
Plan resources
Create an AST-based query plan to filter database results according to user permissions. This tells you exactly what filters to apply in your code.
Set up in minutes
One URL. Then ask Cerbos to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Cerbos from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Cerbos, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Cerbos for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Cerbos URL.
- Step 03
Save and start
Save the connection and enable Cerbos in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"cerbos": {
"url": "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp"
}
}
} - Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Cerbos
Open Agent mode in chat and ask: "Using Cerbos, help me...". 6 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"cerbos": {
"url": "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp"
}
}
} - Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Cerbos
Ask Copilot: "Using Cerbos, help me...". 6 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"cerbos": {
"url": "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp"
}
}
} - Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Cerbos
Open Cascade and ask: "Using Cerbos, help me...". 6 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"cerbos": {
"url": "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp"
}
}
} - Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Cerbos
Ask Cline: "Using Cerbos, help me...". 6 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add cerbos --transport http "https://edge.vinkius.com/vk_preview_y0c5dNo7ENj8oh5gsdkYK0hZAMSRgY44sro1JyED/mcp" - Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Cerbos
Ask Claude: "Using Cerbos, show me...". 6 tools are ready
Where the request belongs
Work Cerbos can move forward.
This is for the security engineer who is tired of manual policy audits and the backend developer who wants to ensure their queries are always compliant with RBAC rules.
Security Engineer
Auditing complex permission sets to ensure no one has over-privileged access.
Backend Developer
Writing database queries that need to respect dynamic user permissions.
DevOps Engineer
Checking instance health and verifying configuration metadata during deployment.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsCerbos (Access Control)
Decouple authorization from your code. Manage policies, check permissions, and audit access control directly through your AI agent.
Permify
Manage fine-grained authorization and access control via Permify. write schemas, manage relation tuples, and perform real-time permission checks.
Permit.io
Orchestrate full-stack authorization, manage RBAC/ReBAC policies, and evaluate permissions in real-time via Permit.io.
OpenFGA (Fine-Grained Auth)
Manage fine-grained authorization with OpenFGA. create stores, define authorization models, and manage relationship tuples directly from your AI agent.
Aserto
Manage authorization policies and evaluate access control decisions via Aserto. run Rego queries, check user permissions, and audit decision logs.
Authing
Cloud-native identity and access management platform. manage users, roles, and security logs via AI.
Bring your own AI
Change the model, client or framework. Keep Cerbos connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Cerbos.
The practical details behind the request, access and result.
What is Cerbos MCP for?
Cerbos MCP lets you manage and audit your authorization policies using natural language. You can ask your AI client to check permissions, generate query plans, or verify security rules without leaving your chat interface.
How can I use Cerbos to check permissions?
You can simply ask your AI agent to verify if a specific user or role can perform an action on a resource. The Connector will check your Cerbos policies and give you a clear allow or deny answer immediately.
Can Cerbos help with my database queries?
Yes. It can generate query plans that tell you exactly what filters to apply to your database results to ensure they comply with your security policies.
Is Cerbos good for RBAC and ABAC?
It is built specifically for both RBAC and ABAC. It helps you manage complex permission logic and ensures your AI agent can evaluate those rules accurately in real time.
How do I connect Cerbos to my AI client?
Once you subscribe to the Connector, you just need to provide your Cerbos instance base URL in your AI client settings. From there, your agent can start interacting with your policies.
Can I audit my security policies with Cerbos?
Absolutely. You can ask your agent to evaluate batches of requests or check specific roles to ensure your policies are behaving exactly as you intended.
Can I check if a specific user has permission to access a resource?
Yes. Use the check_resources capability 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 capability. 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 capability retrieves the version, build date, and commit hash of your connected Cerbos instance.
One connection away
Give your agent a direct line to Cerbos.
Connect Cerbos once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available