How to Use the FunnelCockpit MCP in Vercel AI SDK

Q: How do I connect the FunnelCockpit MCP Server to my Vercel AI SDK project?

Install @ai-sdk/mcp and ai via npm. Initialize the client using createMCPClient with your Vinkius HTTP endpoint, then pass the tools directly into streamText. Don't forget to call mcpClient.close() once the streaming session completes to avoid memory leaks on your Edge Functions.

Q: Can I use the Vercel AI SDK to update FunnelCockpit CRM contacts on the fly?

Yes, your agent can call updatecontact directly inside your streaming text loops. This allows you to modify contact details based on user chat inputs and stream the updated CRM state straight back to your frontend.

Q: How do I verify my API connection is active before running queries?

Have your agent call checkfunnelcockpitstatus at the start of the session. This quick check verifies the API handshake is successful before you attempt to fetch larger datasets like listcontacts.

Stream FunnelCockpit CRM data directly into your React components in real time 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 FunnelCockpit MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time contact rendering with Vercel AI SDK

Using `create_contact` keeps your users from staring at boring loading spinners while you sync leads. When a visitor submits an email on your site, this setup streams the creation event. Your Next.js app initiates the call behind the scenes, returning the fresh CRM record directly to your frontend before the page even thinks about reloading. You can instantly render the contact's custom fields or subscription status in your UI. If you need to fix a typo or append a tag, the agent triggers `update_contact` and pushes the updated payload right into your React state. No polling, no latency, just a clean flow that keeps your signup experience fast.

Live funnel diagnostics via Vercel AI SDK

Pulling layouts with `list_funnels` means you can skip writing heavy API wrappers for your dashboard. By hooking this MCP Server up to your streaming backend, your agent can grab active layouts and render the structure live. The agent reads the page layout with `list_pages` and matches it against your active campaigns. Instead of waiting for a massive API payload to finish downloading, your team watches the funnel architecture load element by element as it streams.

Instant campaign status checks

Querying active sequences with `list_campaigns` lets your marketing team see what is live without logging into another heavy dashboard. The agent spits out the raw campaign names and schedules directly into your chat window. If things look off, the agent runs `check_funnelcockpit_status` to make sure the connection to the German servers is solid. You get an immediate confirmation of API health right in your terminal or web UI, keeping your marketing audits fast and completely transparent.

Setup guide

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

Install `@ai-sdk/mcp` and `ai` via npm. Initialize the client using `createMCPClient` with your Vinkius HTTP endpoint, then pass the tools directly into `streamText`. Don't forget to call `mcpClient.close()` once the streaming session completes to avoid memory leaks on your Edge Functions.

Yes, your agent can call `update_contact` directly inside your streaming text loops. This allows you to modify contact details based on user chat inputs and stream the updated CRM state straight back to your frontend.

Absolutely. The server runs in a V8 Isolate sandbox on Vinkius, which makes it fully compatible with Vercel's Edge network. You can query `get_contact` or list active campaigns without adding cold-start delays to your Next.js API routes.

Have your agent call `check_funnelcockpit_status` at the start of the session. This quick check verifies the API handshake is successful before you attempt to fetch larger datasets like `list_contacts`.

Your CRM contacts and marketing campaign lists are protected by Vinkius's zero-trust sandbox. The SDK communicates over an encrypted HTTP transport, meaning sensitive email addresses and opt-in histories never touch persistent external logs.

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