Bring Authorization
to Vercel AI SDK
Learn how to connect Cerbos to Vercel AI 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 Vercel AI SDK?
The Vercel AI SDK gives every Cerbos tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 6 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Cerbos integration everywhere
- —
Built-in streaming UI primitives let you display Cerbos tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Cerbos in Vercel AI SDK
Cerbos and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Cerbos to Vercel AI 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 Vercel AI 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 Vercel AI 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 Vercel AI SDK
Every tool call from Vercel AI 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 Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
Webflow
10 toolsEquip your AI agent with direct access to Webflow — manage CMS collections, publish sites, and query site analytics without opening the Webflow designer.
Autobound
12 toolsWrite hyper-personalized sales emails in seconds using AI that researches prospects and crafts messages that get replies.
HubSpot Lead Creator
1 toolsThis MCP does exactly one thing: it extracts customer data from conversations and creates a new Contact in your HubSpot CRM. That's its only function. Incredible for turning your AI into an automated sales assistant.
PitchBook
13 toolsAI private market intelligence: research companies, deals, investors, and funds via agents.