How to Use the Froged MCP in Vercel AI SDK

Q: How do I get started with Froged and the Vercel AI SDK?

Install the @ai-sdk/mcp package and point the createMCPClient to your Vinkius endpoint URL. The client will automatically discover the Froged tools like upsertcontact and make them available to your AI.

Q: Can my AI agent create or update contacts in Froged using the Vercel AI SDK?

Yes. The upsertcontact tool is included for this exact purpose. Your agent can take details from a form in your app and use them to create or update a contact record in Froged.

Q: What's the best way to check if the Froged API is online with the Vercel AI SDK?

Use the verifyapistatus tool. It's a simple, fast way for your agent to confirm a connection to Froged before trying to send messages or update contacts. You can show a status indicator in your UI based on the result.

Q: Can I pull knowledge base articles from Froged into my Vercel AI SDK app?

Absolutely. Your agent can call listkbarticles to search and retrieve help documentation. You can use this to build a self-service help widget right inside your application.

Stream Froged customer data directly into your Vercel AI SDK app. Show users live updates instead of loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Froged MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a live customer directory

This MCP server gives your agent tools to pull Froged data right into your UI. You can build a customer profile page that populates in real-time. As the AI client calls `get_contact_details`, the user sees their information appear field by field, no waiting. Use `list_cs_contacts` to stream a list of users into a table component. Because the Vercel AI SDK streams tool results, your interface feels incredibly responsive. It's the difference between a static page and a live dashboard.

Create a real-time support chat UI

Connect your Vercel AI SDK frontend to a live stream of customer support activity. Your agent can use `list_support_conversations` to populate a ticket queue. When a support rep clicks a conversation, `get_chat_details` streams the entire message history into view. When your agent needs to reply, it calls `send_chat_message`. The new message appears instantly in the UI for a true real-time chat experience. You're not just calling an API; you're building a live window into your Froged support desk.

Display live user activity feeds with this MCP Server

Show what users are doing inside your app, as it happens. Your AI agent can call `list_behavioral_events` to get a stream of user actions. This is perfect for building an admin dashboard with a live activity feed. Combine this with `track_custom_event` to let your agent log new events from your app's UI. The user clicks a button, the agent calls the tool, and the event immediately appears in the feed. It closes the loop between user action and system feedback.

Setup guide

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

Install the `@ai-sdk/mcp` package and point the `createMCPClient` to your Vinkius endpoint URL. The client will automatically discover the Froged tools like `upsert_contact` and make them available to your AI.

Yes. The `upsert_contact` tool is included for this exact purpose. Your agent can take details from a form in your app and use them to create or update a contact record in Froged.

Use the `verify_api_status` tool. It's a simple, fast way for your agent to confirm a connection to Froged before trying to send messages or update contacts. You can show a status indicator in your UI based on the result.

Absolutely. Your agent can call `list_kb_articles` to search and retrieve help documentation. You can use this to build a self-service help widget right inside your application.

The server interacts with Froged contact details, support messages, and behavioral event logs. Vinkius secures this by running every tool call in an isolated V8 sandbox. Your Vercel AI SDK app only needs the Vinkius endpoint token, so your Froged API key is never exposed to the client.

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