How to Use the Customers.ai MCP in Vercel AI SDK

Stream identified website visitors and outreach actions directly into your React or Next.js app using 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 Customers.ai MCP to Vercel AI SDK

Create your Vinkius account to connect Customers.ai 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 Customers.ai with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream X-Ray Leads to Your UI

Your Vercel AI SDK client calls `list_xray_leads` to pull anonymous website visitors right as they hit your landing page. Instead of waiting for a batch job, the MCP Server fetches names, emails, and browsing behavior instantly. The data streams straight into your Next.js frontend without a loading state. Getting the details on a specific hit requires the `get_contact` tool. You pass the visitor ID, and the server returns their full profile. That means your sales reps see exactly who is on the site and what they care about, live.

Update Profiles from Chat Interfaces

Managing CRM data via chat starts with `search_contacts` to locate a specific prospect in the database. Users type a name into your custom interface, and the AI retrieves the matching record. From there, the `update_contact_attributes` tool modifies custom fields like company size or budget. Tagging happens just as fast. When a conversation reveals high intent, the agent triggers `add_tag_to_contact` to mark them as a hot lead. If they disqualify themselves, `remove_tag_from_contact` handles the cleanup.

Customers.ai MCP Server Outreach

Sending out communications directly from your web app relies on the `send_text_message` tool. The user types a command, and the AI fires off an SMS to the prospect. You do not need to build a separate messaging backend. Complex payloads go through `send_rich_message` instead. This handles structured JSON, letting you push interactive content or media. Vinkius manages the connection, so your edge functions just call the tools and move on.

Setup guide

Set up Customers.ai 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 Customers.ai 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 Customers.ai 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 Customers.ai. 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 Customers.ai 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 Customers.ai MCP in Vercel AI SDK

Install the @ai-sdk/mcp package and initialize createMCPClient with your HTTP endpoint. Pass the resulting tools directly to streamText. Vinkius handles the underlying authentication.

Yes, they can. When you call the lead listing tools, the SDK streams the chunks directly into your React components. Users see visitor names appear instantly.

It runs perfectly on the Edge. The HTTP transport layer connects to the Vinkius server without heavy Node.js dependencies. You get fast execution times globally.

You format your payload and pass it to the rich message tool. The AI SDK handles the tool call execution, while the server processes the structured JSON. This sends interactive elements straight to the contact.

This server reads and writes names, email addresses, phone numbers, and browsing behavior. Vinkius runs the connection inside a V8 Isolate Sandbox, destroying the environment immediately after your AI client finishes the request.

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