# How to integrate Leadfeeder MCP with Vercel AI SDK v6

```json
{
  "title": "How to integrate Leadfeeder MCP with Vercel AI SDK v6",
  "toolkit": "Leadfeeder",
  "toolkit_slug": "leadfeeder",
  "framework": "Vercel AI SDK",
  "framework_slug": "ai-sdk",
  "url": "https://composio.dev/toolkits/leadfeeder/framework/ai-sdk",
  "markdown_url": "https://composio.dev/toolkits/leadfeeder/framework/ai-sdk.md",
  "updated_at": "2026-05-12T10:17:16.709Z"
}
```

## Introduction

This guide walks you through connecting Leadfeeder to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Leadfeeder agent that can show companies visiting our site today, get detailed visit history for acme corp, enrich this ip address with company info through natural language commands.
This guide will help you understand how to give your Vercel AI SDK agent real control over a Leadfeeder account through Composio's Leadfeeder MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Leadfeeder with

- [ChatGPT](https://composio.dev/toolkits/leadfeeder/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/leadfeeder/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/leadfeeder/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/leadfeeder/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/leadfeeder/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/leadfeeder/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/leadfeeder/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/leadfeeder/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/leadfeeder/framework/cli)
- [Google ADK](https://composio.dev/toolkits/leadfeeder/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/leadfeeder/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/leadfeeder/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/leadfeeder/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/leadfeeder/framework/crew-ai)

## TL;DR

Here's what you'll learn:
- How to set up and configure a Vercel AI SDK agent with Leadfeeder integration
- Using Composio's Tool Router to dynamically load and access Leadfeeder tools
- Creating an MCP client connection using HTTP transport
- Building an interactive CLI chat interface with conversation history management
- Handling tool calls and results within the Vercel AI SDK framework

## What is Vercel AI SDK?

The Vercel AI SDK is a TypeScript library for building AI-powered applications. It provides tools for creating agents that can use external services and maintain conversation state.
Key features include:
- streamText: Core function for streaming responses with real-time tool support
- MCP Client: Built-in support for Model Context Protocol via @ai-sdk/mcp
- Step Counting: Control multi-step tool execution with stopWhen: stepCountIs()
- OpenAI Provider: Native integration with OpenAI models

## What is the Leadfeeder MCP server, and what's possible with it?

The Leadfeeder MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Leadfeeder account. It provides structured and secure access to your website visitor intelligence and lead data, so your agent can identify visiting companies, retrieve lead insights, view visit histories, and analyze custom feed configurations on your behalf.
- Account discovery and management: Instantly retrieve a list of all Leadfeeder accounts you have access to, so your agent always knows where to take action.
- Company identification by IP: Enrich an IP address to find out which company it represents, letting your agent quickly qualify new web visitors or prospects.
- Detailed visit history retrieval: Pull comprehensive visit logs for specific leads—including date ranges—so your agent can surface engagement patterns and recent activity.
- Custom feed analysis: List and review all custom feed configurations associated with your accounts, empowering your agent to segment website visitors according to your sales or marketing strategies.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `LEADFEEDER_GET_ACCOUNT` | Get Account | Tool to retrieve the details of a specific account by ID. Use when you need to get information about a particular Leadfeeder account. |
| `LEADFEEDER_GET_ACCOUNTS` | Get Accounts | Tool to retrieve a list of accounts the user has access to. Use when you need to discover all available Leadfeeder accounts after authentication. |
| `LEADFEEDER_GET_ALL_VISITS` | Get All Visits | Tool to retrieve all visits for a specific lead. Use when you need detailed visit history for a lead, optionally filtered by date range. |
| `LEADFEEDER_GET_COMPANY_INFO_BY_IP` | Get Company Info by IP | Tool to retrieve company information based on an IP address. Use when you need to enrich an IP and obtain its company profile. Returns 404 if no match is found. |
| `LEADFEEDER_GET_CUSTOM_FEEDS` | Get Custom Feeds | Retrieve all custom feeds configured for a Leadfeeder account. Custom feeds are saved filter configurations that help organize and segment company visits. Returns an empty list for accounts without premium features (402), non-existent accounts (404), or accounts with no custom feeds. Use LEADFEEDER_GET_ACCOUNTS first to obtain valid account IDs. |
| `LEADFEEDER_GET_TRACKING_SCRIPT` | Get Tracking Script | Tool to retrieve the website tracking script for a given account. Use when you need to obtain the JavaScript tracking code to be inserted on webpages for visitor tracking. |

## Supported Triggers

None listed.

## Creating MCP Server - Stand-alone vs Composio SDK

The Leadfeeder MCP server is an implementation of the Model Context Protocol that connects your AI agent to Leadfeeder. It provides structured and secure access so your agent can perform Leadfeeder operations on your behalf through a secure, permission-based interface.
With Composio's managed implementation, you don't have to create your own developer app. For production, if you're building an end product, we recommend using your own credentials. The managed server helps you prototype fast and go from 0-1 faster.

## Step-by-step Guide

### 1. Prerequisites

Before you begin, make sure you have:
- Node.js and npm installed
- A Composio account with API key
- An OpenAI API key

### 1. Getting API Keys for OpenAI and Composio

OpenAI API Key
- Go to the [OpenAI dashboard](https://platform.openai.com/settings/organization/api-keys) and create an API key. You'll need credits to use the models, or you can connect to another model provider.
- Keep the API key safe.
Composio API Key
- Log in to the [Composio dashboard](https://dashboard.composio.dev?utm_source=toolkits&utm_medium=framework_docs).
- Navigate to your API settings and generate a new API key.
- Store this key securely as you'll need it for authentication.

### 2. Install required dependencies

First, install the necessary packages for your project.
What you're installing:
- @ai-sdk/openai: Vercel AI SDK's OpenAI provider
- @ai-sdk/mcp: MCP client for Vercel AI SDK
- @composio/core: Composio SDK for tool integration
- ai: Core Vercel AI SDK
- dotenv: Environment variable management
```bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv
```

### 3. Set up environment variables

Create a .env file in your project root.
What's needed:
- OPENAI_API_KEY: Your OpenAI API key for GPT model access
- COMPOSIO_API_KEY: Your Composio API key for tool access
- COMPOSIO_USER_ID: A unique identifier for the user session
```bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here
```

### 4. Import required modules and validate environment

What's happening:
- We're importing all necessary libraries including Vercel AI SDK's OpenAI provider and Composio
- The dotenv/config import automatically loads environment variables
- The MCP client import enables connection to Composio's tool server
```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});
```

### 5. Create Tool Router session and initialize MCP client

What's happening:
- We're creating a Tool Router session that gives your agent access to Leadfeeder tools
- The create method takes the user ID and specifies which toolkits should be available
- The returned mcp object contains the URL and authentication headers needed to connect to the MCP server
- This session provides access to all Leadfeeder-related tools through the MCP protocol
```typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["leadfeeder"],
  });

  const mcpUrl = session.mcp.url;
```

### 6. Connect to MCP server and retrieve tools

What's happening:
- We're creating an MCP client that connects to our Composio Tool Router session via HTTP
- The mcp.url provides the endpoint, and mcp.headers contains authentication credentials
- The type: "http" is important - Composio requires HTTP transport
- tools() retrieves all available Leadfeeder tools that the agent can use
```typescript
const mcpClient = await createMCPClient({
  transport: {
    type: "http",
    url: mcpUrl,
    headers: session.mcp.headers, // Authentication headers for the Composio MCP server
  },
});

const tools = await mcpClient.tools();
```

### 7. Initialize conversation and CLI interface

What's happening:
- We initialize an empty messages array to maintain conversation history
- A readline interface is created to accept user input from the command line
- Instructions are displayed to guide the user on how to interact with the agent
```typescript
let messages: ModelMessage[] = [];

console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
console.log(
  "Ask any questions related to leadfeeder, like summarize my last 5 emails, send an email, etc... :)))\n",
);

const rl = readline.createInterface({
  input: process.stdin,
  output: process.stdout,
  prompt: "> ",
});

rl.prompt();
```

### 8. Handle user input and stream responses with real-time tool feedback

What's happening:
- We use streamText instead of generateText to stream responses in real-time
- toolChoice: "auto" allows the model to decide when to use Leadfeeder tools
- stopWhen: stepCountIs(10) allows up to 10 steps for complex multi-tool operations
- onStepFinish callback displays which tools are being used in real-time
- We iterate through the text stream to create a typewriter effect as the agent responds
- The complete response is added to conversation history to maintain context
- Errors are caught and displayed with helpful retry suggestions
```typescript
rl.on("line", async (userInput: string) => {
  const trimmedInput = userInput.trim();

  if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
    console.log("\nGoodbye!");
    rl.close();
    process.exit(0);
  }

  if (!trimmedInput) {
    rl.prompt();
    return;
  }

  messages.push({ role: "user", content: trimmedInput });
  console.log("\nAgent is thinking...\n");

  try {
    const stream = streamText({
      model: openai("gpt-5"),
      messages,
      tools,
      toolChoice: "auto",
      stopWhen: stepCountIs(10),
      onStepFinish: (step) => {
        for (const toolCall of step.toolCalls) {
          console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
```

## Complete Code

```typescript
import "dotenv/config";
import { openai } from "@ai-sdk/openai";
import { Composio } from "@composio/core";
import * as readline from "readline";
import { streamText, type ModelMessage, stepCountIs } from "ai";
import { createMCPClient } from "@ai-sdk/mcp";

const composioAPIKey = process.env.COMPOSIO_API_KEY;
const composioUserID = process.env.COMPOSIO_USER_ID;

if (!process.env.OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!composioAPIKey) throw new Error("COMPOSIO_API_KEY is not set");
if (!composioUserID) throw new Error("COMPOSIO_USER_ID is not set");

const composio = new Composio({
  apiKey: composioAPIKey,
});

async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["leadfeeder"],
  });

  const mcpUrl = session.mcp.url;

  const mcpClient = await createMCPClient({
    transport: {
      type: "http",
      url: mcpUrl,
      headers: session.mcp.headers, // Authentication headers for the Composio MCP server
    },
  });

  const tools = await mcpClient.tools();

  let messages: ModelMessage[] = [];

  console.log("Chat started! Type 'exit' or 'quit' to end the conversation.\n");
  console.log(
    "Ask any questions related to leadfeeder, like summarize my last 5 emails, send an email, etc... :)))\n",
  );

  const rl = readline.createInterface({
    input: process.stdin,
    output: process.stdout,
    prompt: "> ",
  });

  rl.prompt();

  rl.on("line", async (userInput: string) => {
    const trimmedInput = userInput.trim();

    if (["exit", "quit", "bye"].includes(trimmedInput.toLowerCase())) {
      console.log("\nGoodbye!");
      rl.close();
      process.exit(0);
    }

    if (!trimmedInput) {
      rl.prompt();
      return;
    }

    messages.push({ role: "user", content: trimmedInput });
    console.log("\nAgent is thinking...\n");

    try {
      const stream = streamText({
        model: openai("gpt-5"),
        messages,
        tools,
        toolChoice: "auto",
        stopWhen: stepCountIs(10),
        onStepFinish: (step) => {
          for (const toolCall of step.toolCalls) {
            console.log(`[Using tool: ${toolCall.toolName}]`);
          }
          if (step.toolCalls.length > 0) {
            console.log(""); // Add space after tool calls
          }
        },
      });

      for await (const chunk of stream.textStream) {
        process.stdout.write(chunk);
      }

      console.log("\n\n---\n");

      // Get final result for message history
      const response = await stream.response;
      if (response?.messages?.length) {
        messages.push(...response.messages);
      }
    } catch (error) {
      console.error("\nAn error occurred while talking to the agent:");
      console.error(error);
      console.log(
        "\nYou can try again or restart the app if it keeps happening.\n",
      );
    } finally {
      rl.prompt();
    }
  });

  rl.on("close", async () => {
    await mcpClient.close();
    console.log("\n👋 Session ended.");
    process.exit(0);
  });
}

main().catch((err) => {
  console.error("Fatal error:", err);
  process.exit(1);
});
```

## Conclusion

You've successfully built a Leadfeeder agent using the Vercel AI SDK with streaming capabilities! This implementation provides a powerful foundation for building AI applications with natural language interfaces and real-time feedback.
Key features of this implementation:
- Real-time streaming responses for a better user experience with typewriter effect
- Live tool execution feedback showing which tools are being used as the agent works
- Dynamic tool loading through Composio's Tool Router with secure authentication
- Multi-step tool execution with configurable step limits (up to 10 steps)
- Comprehensive error handling for robust agent execution
- Conversation history maintenance for context-aware responses
You can extend this further by adding custom error handling, implementing specific business logic, or integrating additional Composio toolkits to create multi-app workflows.

## How to build Leadfeeder MCP Agent with another framework

- [ChatGPT](https://composio.dev/toolkits/leadfeeder/framework/chatgpt)
- [OpenAI Agents SDK](https://composio.dev/toolkits/leadfeeder/framework/open-ai-agents-sdk)
- [Claude Agent SDK](https://composio.dev/toolkits/leadfeeder/framework/claude-agents-sdk)
- [Claude Code](https://composio.dev/toolkits/leadfeeder/framework/claude-code)
- [Claude Cowork](https://composio.dev/toolkits/leadfeeder/framework/claude-cowork)
- [Codex](https://composio.dev/toolkits/leadfeeder/framework/codex)
- [OpenClaw](https://composio.dev/toolkits/leadfeeder/framework/openclaw)
- [Hermes](https://composio.dev/toolkits/leadfeeder/framework/hermes-agent)
- [CLI](https://composio.dev/toolkits/leadfeeder/framework/cli)
- [Google ADK](https://composio.dev/toolkits/leadfeeder/framework/google-adk)
- [LangChain](https://composio.dev/toolkits/leadfeeder/framework/langchain)
- [Mastra AI](https://composio.dev/toolkits/leadfeeder/framework/mastra-ai)
- [LlamaIndex](https://composio.dev/toolkits/leadfeeder/framework/llama-index)
- [CrewAI](https://composio.dev/toolkits/leadfeeder/framework/crew-ai)

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.
- [Emelia](https://composio.dev/toolkits/emelia) - Emelia is an all-in-one B2B prospecting platform for cold-email, LinkedIn outreach, and prospect research. It streamlines outbound campaigns so you can find, engage, and warm up leads faster.
- [Findymail](https://composio.dev/toolkits/findymail) - Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.
- [Freshdesk](https://composio.dev/toolkits/freshdesk) - Freshdesk is customer support software with ticketing and automation tools. It helps teams streamline helpdesk operations for faster, better customer support.
- [Fullenrich](https://composio.dev/toolkits/fullenrich) - FullEnrich is a B2B contact enrichment platform that aggregates emails and phone numbers from 15+ data vendors. Instantly find and verify lead contact data to boost your outreach.
- [Gatherup](https://composio.dev/toolkits/gatherup) - GatherUp is a customer feedback and online review management platform. It helps businesses boost their reputation by streamlining how they collect and manage customer feedback.
- [Getprospect](https://composio.dev/toolkits/getprospect) - Getprospect is a business email discovery tool with LinkedIn integration. Use it to quickly find and verify professional email addresses.
- [Gleap](https://composio.dev/toolkits/gleap) - Gleap is an all-in-one customer feedback tool for apps and websites. It helps you understand user pain points and improve software through direct, actionable insights.
- [Handwrytten](https://composio.dev/toolkits/handwrytten) - Handwrytten automates handwritten cards and notes using robotic penmanship. Save time while adding a personal touch to your customer or team communications.
- [Heyy](https://composio.dev/toolkits/heyy) - Heyy is a messaging automation platform for WhatsApp, SMS, Messenger, and Instagram. Streamline customer conversations across channels with one tool.
- [La Growth Machine](https://composio.dev/toolkits/lagrowthmachine) - La Growth Machine automates multi-channel sales outreach and routine tasks for sales teams. Streamline your workflow and focus on closing more deals.
- [LeadBoxer](https://composio.dev/toolkits/leadboxer) - LeadBoxer is a lead generation platform that reveals real-time info about your website visitors. It turns anonymous traffic into actionable business data for smarter sales efforts.
- [LeadIQ](https://composio.dev/toolkits/leadiq) - LeadIQ is a B2B prospecting platform that helps you find and enrich leads. It streamlines gathering accurate company and contact info for smarter outreach.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Leadfeeder MCP?

With a standalone Leadfeeder MCP server, the agents and LLMs can only access a fixed set of Leadfeeder tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Leadfeeder and many other apps based on the task at hand, all through a single MCP endpoint.

### Can I use Tool Router MCP with Vercel AI SDK v6?

Yes, you can. Vercel AI SDK v6 fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Leadfeeder tools.

### Can I manage the permissions and scopes for Leadfeeder while using Tool Router?

Yes, absolutely. You can configure which Leadfeeder scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

### How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Leadfeeder data and credentials are handled as safely as possible.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)