How to Use the Leadfeeder MCP in Vercel AI SDK

Stream visitor data straight into your UI with the Leadfeeder MCP Server for 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 Leadfeeder MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time lead discovery in your UI

Feed company visit data directly into your frontend components as the AI processes it. When your user asks who is browsing, the agent uses `list_leads` to pull active accounts and displays them instantly without waiting for a backend refresh. Your interface stays snappy because the data flows over the stream. You aren't just logging information; you are building live dashboards where the agent updates the view as soon as `get_lead` fetches the latest firmographic details.

Targeted account monitoring

Filter traffic on the fly by hitting your custom feeds. The agent calls `list_custom_feeds` to identify high-intent segments, then drills down into specific behaviors using `get_custom_feed` to show only the companies that matter to your users. This keeps your application focused on relevant prospects. By connecting these tools to your UI, you give users the ability to see exactly which companies trigger their specific criteria in real-time.

Manage tracking scripts programmatically

Check your site's health by pulling the current installation status through your application. The agent uses `get_tracking_script` to verify the code is present, ensuring your data pipeline remains active. If the script is missing, the agent can flag it immediately. This allows developers to build diagnostic views where the state of your Leadfeeder integration is always visible to the end user.

Setup guide

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

You initialize the client and pass the tool set directly into your `streamText` function. This allows the agent to call `list_leads` and pipe the results into your React components via the stream.

Yes, you can define an array of tools in your agent configuration. The model will pick the right ones, like `get_account` or `list_account_visits`, based on the user's intent.

It does. Since the MCP server provides a standard interface, your edge-deployed agent can execute tools like `list_leads` with minimal latency.

Your API tokens stay on the server side. The MCP server only exposes the specific tools you authorize, keeping your visitor lists and account IDs private.

It accesses your B2B visitor logs, organization names, and custom feed definitions. We never store this data; it passes through the encrypted tunnel directly to your agent.

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