How to Use the Nutshell CRM MCP in Vercel AI SDK

Q: How do I initialize the Nutshell CRM MCP Server with the Vercel AI SDK?

Install the package using npm install ai @ai-sdk/mcp and configure the client. Use createMCPClient to point to the Vinkius endpoint, then pass the tools directly into streamText.

Q: How do I handle user authentication for Nutshell CRM in the Vercel AI SDK?

You configure the authProvider option within the SDK setup. This securely maps your user's specific CRM credentials to the Vinkius session, allowing safe execution of tools like listactivities.

Q: Do I need to manually close the connection after running a search?

Yes, always call mcpClient.close() when your execution loop finishes. This prevents memory leaks and ensures your serverless functions spin down cleanly.

Feed live Nutshell CRM data directly into your Next.js frontend 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 Nutshell CRM MCP to Vercel AI SDK

Create your Vinkius account to connect Nutshell CRM 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 Nutshell CRM with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream active leads to your Next.js UI

The `list_leads` tool pulls active sales pipelines straight from your Nutshell CRM account. Your AI client calls this tool to retrieve deal sizes, stages, and close dates, instantly passing the raw data payload to your frontend. Because the Vercel AI SDK streams responses, your users watch lead lists populate cell-by-cell in real-time. You don't have to build complex loading spinners or wait for a slow backend database query to complete before rendering the UI.

Instantly fetch customer details on the Edge

The `get_contact_details` tool fetches complete profiles for any person stored in your CRM. It retrieves emails, phone numbers, and past interactions with zero middleware required. Deploying this on Vercel Edge Functions means your agent resolves queries with minimal latency. The SDK handles the raw JSON from the MCP Server and pipes it directly into your React components for immediate rendering.

Search your entire CRM via this MCP Server

The `universal_search` tool scans across accounts, contacts, and leads in Nutshell CRM to find matching records. Your agent uses this single endpoint to find scattered data without running multiple slow API queries. When integrated with the Vercel AI SDK, users get an interactive, search-as-you-type experience. The agent updates the UI dynamically as the user types, displaying accounts found via `list_accounts` alongside active leads.

Setup guide

Set up Nutshell CRM 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 Nutshell CRM 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 Nutshell CRM 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 Nutshell CRM. 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 Nutshell CRM 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 Nutshell CRM MCP in Vercel AI SDK

Install the package using `npm install ai @ai-sdk/mcp` and configure the client. Use `createMCPClient` to point to the Vinkius endpoint, then pass the tools directly into `streamText`.

Yes, this MCP Server is compatible with edge runtimes. The lightweight HTTP transport allows your agent to query the server without hitting cold start delays.

You configure the `authProvider` option within the SDK setup. This securely maps your user's specific CRM credentials to the Vinkius session, allowing safe execution of tools like `list_activities`.

Yes, always call `mcpClient.close()` when your execution loop finishes. This prevents memory leaks and ensures your serverless functions spin down cleanly.

Every request to read your leads, contacts, accounts, and activities runs inside an isolated, ephemeral V8 sandbox on Vinkius. Your API keys are encrypted at rest and never exposed to the LLM or frontend 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