How to Use the MintMCP MCP in Vercel AI SDK

Q: Can MintMCP handle audit logging for Vercel AI SDK apps?

Yes. You can trigger mintmcpfetchauditlogs whenever your application needs to verify historical access. It pulls the telemetry data directly into your runtime.

Q: Does MintMCP restrict tool access for Vercel AI SDK users?

It does. By using mintmcpgettoolpolicy, you define exactly what an agent can touch. If a tool isn't in the policy, the gateway blocks the request entirely.

Q: How do I revoke access tokens for a Vercel AI SDK session?

Call mintmcprevokeaccesstoken from your backend logic. This immediately kills the active OAuth flow and prevents further requests from that session.

MintMCP brings enterprise-grade security to your Vercel AI SDK projects by locking down every tool execution at the gateway.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MintMCP MCP to Vercel AI SDK

Create your Vinkius account to connect MintMCP 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 MintMCP with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time security evaluation for your UI

Stop passing raw data to your frontend without a check. Use `mintmcp_eval_guardrail` to scrub sensitive strings before they ever reach your React or Next.js components. Your users see the output instantly, but you get the peace of mind that every data point passed through `mintmcp_run_tool_action` has cleared your internal security policy.

Audit your AI traffic in the browser

Keep a tight grip on what your agents are doing by calling `mintmcp_fetch_audit_logs`. You get a clean dump of every access event directly in your TypeScript environment. This lets you track exactly who touched which resource. It’s perfect for showing compliance metrics inside your dashboard without writing custom logging middleware.

Manage virtual servers via code

Your AI client needs to know which tools are available. Use `mintmcp_list_available_tools` and `mintmcp_list_virtual_servers` to dynamically update your UI based on the specific permissions granted to the current session. It’s simple to swap environments or restrict access on the fly. Just fetch the latest `mintmcp_get_tool_policy` to ensure your SDK implementation stays within your organization's boundaries.

Setup guide

Set up MintMCP 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 MintMCP 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 MintMCP 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 MintMCP. 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 MintMCP 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 MintMCP MCP in Vercel AI SDK

Use the built-in auth provider in the Vercel AI SDK to supply your endpoint token. MintMCP validates this token before allowing any tool calls, keeping your gateway locked down.

Yes. You can trigger `mintmcp_fetch_audit_logs` whenever your application needs to verify historical access. It pulls the telemetry data directly into your runtime.

It does. By using `mintmcp_get_tool_policy`, you define exactly what an agent can touch. If a tool isn't in the policy, the gateway blocks the request entirely.

Call `mintmcp_revoke_access_token` from your backend logic. This immediately kills the active OAuth flow and prevents further requests from that session.

MintMCP uses a zero-trust model. It evaluates PII-redaction via `mintmcp_eval_guardrail` for every request, ensuring raw user inputs never leak into your downstream logs.

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