How to Use the Cerbos (Access Control) MCP in Vercel AI SDK

Q: How do I use Cerbos (Access Control) with the Vercel AI SDK to check multiple permissions at once?

Your agent should use the checkresources tool. You pass it a principal, and a list of resources with actions you want to check. Cerbos will return an allow/deny result for each one in a single call.

Q: Can I build a UI that lets admins enable or disable policies with Cerbos (Access Control) and the Vercel AI SDK?

Yes, that's a great use case. Your agent can call the enablepolicy and disablepolicy tools. Since the Vercel AI SDK streams results, you can update the UI instantly to reflect the policy's new state.

Q: What's the best way to show policy details in a React component?

Have your agent call getpolicy with a policy ID. The tool returns the full policy definition. You can then stream this data into a state variable and render it inside a pre-formatted code block in your component.

Q: How do I get a query plan from Cerbos (Access Control) using the Vercel AI SDK?

Use the planresources tool. It generates a query plan that you can use to efficiently fetch only the resources a user is allowed to see from your database. It's a smart way to build secure data filters.

Manage Cerbos policies and see access changes update in your UI in real-time with the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cerbos (Access Control) MCP to Vercel AI SDK

Create your Vinkius account to connect Cerbos (Access Control) to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Cerbos (Access Control) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Modify Policies Directly from Your App

Add, update, or disable authorization policies on the fly. Your agent can use `add_policy`, `update_policy`, and `disable_policy` to change access rules without a code deploy. You can also fetch a specific rule with `get_policy` to show users what they can and can't do. Because the Vercel AI SDK streams tool results, your users see these policy changes happen live. A status indicator in your Next.js app can flip from 'pending' to 'active' the moment the `enable_policy` tool completes. No page reloads, no waiting.

Run Live Access Checks with This MCP Server

Check permissions for any user and any resource right from your UI. Your agent calls `check_resources` with a principal and a list of actions. Cerbos returns a simple allowed or denied for each, which you can use to conditionally render buttons or data. This is perfect for building dynamic UIs. Instead of just hiding a button, your agent can explain *why* it's disabled by checking the policy. It then streams that explanation directly into a tooltip component using the Vercel AI SDK.

Audit and Monitor Cerbos Health

Keep an eye on your authorization service. Your agent can pull operational data using `get_health` for a quick status check or grab detailed Prometheus data with `get_metrics`. For security reviews, you can pull audit history with `list_audit_logs`. Build an internal dashboard that streams this data. Hook up the `get_server_info` and `get_health` tools and watch your Cerbos instance status update in real-time on your screen. It's a live view into your access control layer, powered by this MCP server.

Setup guide

Set up Cerbos (Access Control) MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Cerbos (Access Control) tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Cerbos (Access Control) transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Cerbos. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Cerbos (Access Control) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Cerbos (Access Control) MCP in Vercel AI SDK

Your agent should use the `check_resources` tool. You pass it a principal, and a list of resources with actions you want to check. Cerbos will return an allow/deny result for each one in a single call.

Yes, that's a great use case. Your agent can call the `enable_policy` and `disable_policy` tools. Since the Vercel AI SDK streams results, you can update the UI instantly to reflect the policy's new state.

Have your agent call `get_policy` with a policy ID. The tool returns the full policy definition. You can then stream this data into a state variable and render it inside a pre-formatted code block in your component.

Use the `plan_resources` tool. It generates a query plan that you can use to efficiently fetch only the resources a user is allowed to see from your database. It's a smart way to build secure data filters.

The server processes your authorization data: policies, schemas, and the principal/resource details you send for checks. Vinkius runs each MCP server in an ephemeral, zero-trust sandbox. Your connection is always encrypted, and your Vinkius token handles all the authentication.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript