How to Use the Custify MCP in Vercel AI SDK

Q: How do I connect Custify to the Vercel AI SDK?

Install @ai-sdk/mcp and instantiate the client. Pass the Vinkius endpoint using createMCPClient({ transport: { type: "http", url: "..." } }). Then feed mcpClient.tools() right into your generation function.

Q: Can the Vercel AI SDK stream Custify health scores?

Yes. When your agent calls getcustomerdetails, the tool result streams back to the UI immediately. Your frontend renders the health metrics without waiting for the entire response to finish.

Stream live customer health metrics and account data directly into your React apps using 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 Custify MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Custify Data with Vercel AI SDK

Fetching customer profiles with `get_customer_details` usually means staring at loading spinners. You fix that by passing this tool from the MCP Server directly into `streamText`. The Vercel AI SDK pushes the health scores and segment memberships straight to your Next.js frontend as they resolve. Building a live dashboard gets much easier when the agent handles the fetching. Call `list_customer_kpis` and watch the metric definitions render block by block in your UI. Just remember to run `mcpClient.close()` when the stream finishes.

Search and Create Accounts Live

Finding accounts fast requires hooking `search_customers_by_keyword` to a text input. Let your agent stream matching profiles instantly as the user types. The client sees names and emails appear before they even finish the query. Adding new records works the same way. When a user tells your agent to add a contact, `create_customer_profile` mutates the database using the MCP Server. The UI updates in real-time, showing the new customer ID without a full page refresh.

Expose CRM Notes via MCP Server

Building internal tools requires surfacing context via `list_customer_notes` on demand. You give your agent access to this tool so it can pull authorship metadata and internal communications. The Vercel AI SDK handles the tool calling while your Edge Function stays lean. Managing organizational hierarchies takes just a few lines of code. Fetching `list_companies` alongside `list_people` gives your agent the context to map out account relationships. Vinkius handles the underlying server infrastructure so you just focus on the React components.

Setup guide

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

Install `@ai-sdk/mcp` and instantiate the client. Pass the Vinkius endpoint using `createMCPClient({ transport: { type: "http", url: "..." } })`. Then feed `mcpClient.tools()` right into your generation function.

Yes. When your agent calls `get_customer_details`, the tool result streams back to the UI immediately. Your frontend renders the health metrics without waiting for the entire response to finish.

The error bubbles up through the tool call block. You catch it in your frontend error boundary or handle it within the `streamText` lifecycle. The agent can then retry the mutation automatically.

It runs perfectly in Edge environments. The HTTP transport works natively without requiring Node.js built-ins. You just need to set your Vinkius auth token in your environment variables.

Your agent touches sensitive health scores and churn probabilities through a V8 Isolate Sandbox. Every connection to the endpoint is ephemeral and destroyed immediately after the request. Zero data rests on our infrastructure.

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