How to Use the Apideck MCP in Vercel AI SDK

Pull CRM data and manage Vault sessions directly in your Vercel AI SDK frontends for live streaming UI updates.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Apideck MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream CRM data into Vercel AI SDK

Feed contact lists from various CRMs directly into your React or Next.js interface. Your users watch `list_crm_contacts` results populate in real-time as the model streams the response. Stop waiting for loading spinners. Because this MCP server integrates with your edge functions, the data hits your UI the moment the tool finishes executing.

Handle Vault sessions via AI SDK

Control your secure connections without leaving your TypeScript code. Trigger `create_vault_session` to initiate user auth flows or use `get_vault_connection` to verify account states. Everything stays within your streaming pipeline. You manage the session lifecycle while the agent handles the logic.

Execute proxy requests on the fly

Bypass complex middleware by routing external API calls through `execute_proxy`. It hits the target endpoint and returns the payload to your Vercel AI SDK agent instantly. You avoid writing custom backend routes for every third-party service. Just point the tool at the resource and let the agent parse the output.

Setup guide

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

Install the MCP packages and define your endpoint. You'll pass the client instance into your streamText functions to make the tools available.

Yes. You can use the Vault tools to open and track connections securely. The SDK handles the session tokens during the request.

It does. The tool outputs stream directly into your components. You won't see any lag between the tool finishing and the data appearing.

You can grab contacts from any platform supported by the Unified CRM API. Just call the list tool and map the results to your frontend.

Your connection strings and credentials stay inside the Vault. We use encrypted sessions to ensure your CRM data remains isolated from your public-facing traffic.

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