How to Use the Funil de Vendas MCP in Vercel AI SDK

Q: How do I show a list of deals in my app with Funil de Vendas and the Vercel AI SDK?

Your AI client calls the listopportunities tool from this MCP server. The AI SDK then streams the array of opportunities, which you can render into a list in your React or Svelte components as the data arrives.

Q: What's the best way to handle custom fields from Funil de Vendas with the Vercel AI SDK?

First, have your agent call listcustomfields to get the available fields and their IDs. Then, you can use that information to correctly structure calls to createopportunity or updateopportunity, ensuring the data lands in the right place.

Q: Is this Funil de Vendas MCP server difficult to connect to?

No, it's straightforward. You'll use createMCPClient with your Vinkius endpoint URL. The client handles authentication, and you just pass the tools to the generateText or streamText functions.

Stop showing loading spinners. Stream Funil de Vendas pipeline data directly into your UI with 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 Funil de Vendas MCP to Vercel AI SDK

Create your Vinkius account to connect Funil de Vendas 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 Funil de Vendas with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Live Sales Dashboards

Give your users a real-time view of their sales pipeline. As your agent calls `list_opportunities` or `list_companies`, the data streams directly into your React or Next.js components. No page reloads, no waiting. The UI builds itself as the information arrives. This isn't just about lists. You can build summary cards that populate instantly with data from `get_people_stats`. Or, watch a detailed view get filled out as your AI client runs `get_opportunity` in the background. Your users see the agent working, not a blank screen.

Create Records from Conversation

Let users manage their CRM by just talking to your app. An agent can listen to a user's request, then call `create_person` or `create_company` and stream the result right back to the UI. The new contact appears in a list the second it's created in Funil de Vendas. It’s a better way to handle data entry. A user can describe a new deal, and your agent uses `create_opportunity` to add it to the pipeline. Because the AI SDK streams the tool output, you can give immediate confirmation that the record was created, complete with its new ID.

Interactive Pipeline Management with this MCP Server

Build an interface where users can update their deals without touching a form. Your agent can ask for the next step, then use the `update_opportunity` tool to change the deal's stage. You can even fetch the available stages first by calling `list_funnels`. This makes CRM updates feel less like a chore. The entire interaction happens through your AI-powered interface, with the Vercel AI SDK rendering the changes as they happen. It’s a direct link between your user, your agent, and your Funil de Vendas data.

Setup guide

Set up Funil de Vendas 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 Funil de Vendas 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 Funil de Vendas 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 Funil de Vendas. 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 Funil de Vendas 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 Funil de Vendas MCP in Vercel AI SDK

Your AI client calls the `list_opportunities` tool from this MCP server. The AI SDK then streams the array of opportunities, which you can render into a list in your React or Svelte components as the data arrives.

Yes. You build a UI that captures the user's intent, and your agent invokes the `create_person` and `create_company` tools. The new record is created in Funil de Vendas, and the result is streamed back to your UI for instant confirmation.

First, have your agent call `list_custom_fields` to get the available fields and their IDs. Then, you can use that information to correctly structure calls to `create_opportunity` or `update_opportunity`, ensuring the data lands in the right place.

No, it's straightforward. You'll use `createMCPClient` with your Vinkius endpoint URL. The client handles authentication, and you just pass the tools to the `generateText` or `streamText` functions.

Vinkius processes all tool calls in an ephemeral, zero-trust sandbox. When your app uses the Vercel AI SDK to call `create_person` or `list_opportunities`, the contact and deal data is handled only for that single request and is not stored. Each MCP call is isolated.

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