How to integrate Productlane MCP with Vercel AI SDK v6

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Productlane logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Productlane to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Productlane agent that can open productlane widget for user feedback, display specific docs article in widget, register listener for widget submit events through natural language commands.

This guide will help you understand how to give your Vercel AI SDK agent real control over a Productlane account through Composio's Productlane MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Productlane with

TL;DR

Here's what you'll learn:
  • How to set up and configure a Vercel AI SDK agent with Productlane integration
  • Using Composio's Tool Router to dynamically load and access Productlane 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 Productlane MCP server, and what's possible with it?

The Productlane MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Productlane account. It provides structured and secure access to your customer feedback and support workflows, so your agent can programmatically control the Productlane widget, surface documentation, listen for widget events, and manage user interaction—all on your behalf.

  • Dynamic widget control: Let your agent open, close, enable, disable, or toggle the Productlane widget in response to customer or team actions.
  • Contextual docs surfacing: Automatically display specific Productlane documentation articles within the widget to assist users at the right moment.
  • Event-driven automation: Register or remove event listeners so your agent can react to widget events like open, close, submit, or widget load—enabling smart, real-time workflows.
  • Seamless widget experience: Programmatically manage the widget's state across your app to ensure users always get the right support touchpoint.
  • Custom interaction flows: Use the widget's event system to trigger your own logic or follow-ups based on how users interact with Productlane support.

Supported Tools & Triggers

Tools
Create Changelog EntryTool to create a new changelog entry in Productlane.
Create CompanyTool to create a new company in Productlane.
Create ContactTool to create a new contact in your Productlane workspace with optional company linking.
Create FeedbackTool to create new feedback in Productlane.
Create InsightTool to create a new insight/thread in Productlane workspace.
Create ThreadTool to create a new thread in Productlane.
Create UpvoteTool to create an upvote for a project or issue.
Delete CompanyTool to delete a company by its unique ID.
Delete ContactTool to delete a contact by ID.
Delete UpvoteTool to delete an upvote by its unique ID.
Enable Productlane WidgetTool to enable the Productlane widget.
Get ChangelogTool to retrieve a published changelog by ID from Productlane.
Get Company by IDTool to retrieve a company by its unique ID.
Get ContactTool to retrieve a contact by ID or email from Productlane.
Get Help Center ArticleTool to retrieve a help center article by its ID.
Get InsightTool to retrieve an insight/thread by its ID.
Get Issue by IDTool to retrieve a specific issue by its ID from a workspace.
Get Linear Customer OptionsTool to retrieve available Linear customer statuses and tiers for your workspace.
Get ProjectTool to retrieve a project by its ID from a workspace.
Get WorkspaceTool to fetch workspace details by ID.
Invite User to WorkspaceTool to invite a new user to your Productlane workspace.
List ChangelogsTool to list all published changelogs for a workspace by ID.
List CompaniesTool to list all companies in Productlane.
List contactsTool to retrieve all contacts for your workspace.
List Help Center ArticlesTool to list all help center articles for a specific workspace.
List InsightsTool to list all threads/insights for your workspace with optional filtering.
List Productlane IssuesTool to retrieve all issues from a Productlane workspace.
List Workspace MembersTool to retrieve all members of your workspace with their roles and user information.
List ProjectsTool to retrieve all projects within a workspace.
Update CompanyTool to update an existing company record in Productlane by its unique identifier.
Update ContactTool to update an existing contact in Productlane.
Update InsightTool to update an existing insight (thread) by ID.
Close Productlane WidgetTool to close the Productlane widget.
Disable Productlane WidgetTool to disable the Productlane widget across the entire page.
Widget off eventTool to remove a previously registered widget event listener.
Register Widget Event ListenerTool to register a listener for Productlane widget events.
Open Productlane WidgetTool to generate a JavaScript snippet that opens the Productlane widget.
Open Productlane Docs Article in WidgetTool to open a specific docs article in the Productlane widget.
Toggle Productlane WidgetTool to toggle the Productlane widget between open and closed states.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

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

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard 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.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.

Install required dependencies

bash
npm install @ai-sdk/openai @ai-sdk/mcp @composio/core ai dotenv

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

Set up environment variables

bash
OPENAI_API_KEY=your_openai_api_key_here
COMPOSIO_API_KEY=your_composio_api_key_here
COMPOSIO_USER_ID=your_user_id_here

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

Import required modules and validate environment

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,
});
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

Create Tool Router session and initialize MCP client

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

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Productlane 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 Productlane-related tools through the MCP protocol

Connect to MCP server and retrieve tools

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();
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 Productlane tools that the agent can use

Initialize conversation and CLI interface

typescript
let messages: ModelMessage[] = [];

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

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

rl.prompt();
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

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

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);
});
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 Productlane 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

Complete Code

Here's the complete code to get you started with Productlane and Vercel AI SDK:

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: ["productlane"],
  });

  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 productlane, 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 Productlane 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 Productlane MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Productlane MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Productlane MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Productlane MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Productlane MCP with Claude Cowork

Codex logo

Codex

Use Productlane MCP with Codex

OpenClaw logo

OpenClaw

Use Productlane MCP with OpenClaw

Hermes logo

Hermes

Use Productlane MCP with Hermes

CLI logo

CLI

Use Productlane MCP with CLI

Google ADK logo

Google ADK

Use Productlane MCP with Google ADK

LangChain logo

LangChain

Use Productlane MCP with LangChain

Mastra AI logo

Mastra AI

Use Productlane MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Productlane MCP with LlamaIndex

CrewAI logo

CrewAI

Use Productlane MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Productlane MCP?

With a standalone Productlane MCP server, the agents and LLMs can only access a fixed set of Productlane tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Productlane 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 Productlane tools.

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

Yes, absolutely. You can configure which Productlane 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 Productlane data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗