How to Use the Close MCP in Vercel AI SDK

Q: How do I get started with the Close MCP Server and the Vercel AI SDK?

First, install the SDK packages. Then, use createMCPClient with the Vinkius URL for this server. You can pass the tools from mcpClient.tools() directly to the generateText or streamText functions.

Q: Is there a way to filter leads when I list them from Close with the Vercel AI SDK?

The listleads tool provided by this MCP server pulls all leads. To filter them, you'd do it on your end after receiving the full list from your agent. Your application code has full control over the data once it's returned.

Stream Close CRM data directly into your Vercel AI SDK app. Build sales tools that update in real time, not after a loading spinner.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Close MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a Live Sales Dashboard

This MCP Server connects your UI to your sales pipeline. You can build components that populate with fresh data as it arrives from Close. Your users won't have to refresh the page to see what's new. Use `list_leads` and `list_opportunities` to stream sales data straight into your React or Next.js components. The Vercel AI SDK lets you show leads and deals appearing one by one. It's perfect for building a dashboard that feels alive and gives your sales team an immediate view of their pipeline.

Add Leads from Any UI

Let your sales team add leads without ever leaving your app. With this server, your agent can take info from a form and send it directly to your CRM. No context switching, just a faster way to capture new business. You give your agent the `create_lead` tool. When a user submits a form, the agent creates the lead in Close. Use `get_lead_details` to immediately pull back the new record and confirm it was created correctly, right in the UI.

Personalize the Sales Experience

Your app can know which sales rep is using it. This lets you build UIs that are tailored to a specific person's accounts, tasks, and permissions. It makes your tool feel like it was built just for them. The `get_current_user` tool fetches the profile of the authenticated user. You can use this data to filter lists, show their specific `list_crm_tasks`, or just display their name in the corner of the app. It's a simple way to make a generic tool feel personal.

Setup guide

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

First, install the SDK packages. Then, use `createMCPClient` with the Vinkius URL for this server. You can pass the tools from `mcpClient.tools()` directly to the `generateText` or `streamText` functions.

Yes, that's exactly what this is for. The AI SDK is designed for streaming tool results. When your agent uses `list_leads`, the data will flow into your UI in real time, which is great for building responsive dashboards.

The Close API will return an error. Your code that calls the Vercel AI SDK function should handle this, just like any other API error. The server itself just passes the request and response through.

The `list_leads` tool provided by this MCP server pulls all leads. To filter them, you'd do it on your end after receiving the full list from your agent. Your application code has full control over the data once it's returned.

Your lead, opportunity, and task data is sent from Close to Vinkius and then to your application. Vinkius servers are ephemeral and don't store your data. The connection is secured, but remember that the data will be present in memory in your Vercel Edge Function during 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