How to integrate Productboard 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

Productboard logo
Vercel AI SDK logo
divider

Introduction

This guide walks you through connecting Productboard to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Productboard agent that can create a new feature idea in productboard, list all features in the current release, add customer feedback to a specific feature through natural language commands.

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

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

Also integrate Productboard with

TL;DR

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

The Productboard MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Productboard account. It provides structured and secure access to your product management workspace, so your agent can perform actions like managing feature ideas, collecting user feedback, prioritizing roadmap items, and aligning strategic goals on your behalf.

  • Centralized feedback collection: Let your agent gather, aggregate, and organize product feedback from stakeholders and customers, so nothing slips through the cracks.
  • Feature and idea management: Enable your agent to create, update, categorize, and prioritize feature ideas or product requests in your Productboard workspace.
  • Roadmap planning and alignment: Ask your agent to assist in building and updating product roadmaps, ensuring initiatives align with business objectives and customer needs.
  • Insightful prioritization workflows: Have the agent score, sort, and recommend features for development using built-in prioritization frameworks and customer impact data.
  • Collaboration and stakeholder updates: Empower your agent to share status updates, progress changes, and new plans with internal teams and stakeholders directly from Productboard.

Supported Tools & Triggers

Tools
Add Note FollowersTool to add multiple followers to a Productboard note.
Add Note TagAdds a tag to a Productboard note for categorization and organization.
Create Company in ProductboardTool to create a new company in Productboard.
Create Company Custom FieldTool to create a new custom field for companies.
Create ComponentTool to create a new (sub)component under a product or component.
Create Entity RelationshipTool to create a relationship between two entities in Productboard.
Create Entity (v2)Tool to create a new entity in Productboard using the v2 API.
Create FeatureTool to create a new feature or subfeature in Productboard.
Create Feature-Objective LinkTool to create a link between a feature and an objective (OKR).
Create Note LinkTool to create a link between a note and an entity.
Create Note (v2)Tool to create a new note in Productboard using the v2 API.
Create ObjectiveTool to create a new objective in Productboard.
Create Objective-Feature LinkTool to create a new link between an objective and a feature.
Create ReleaseTool to create a new release in Productboard.
Create UserTool to create a new user in Productboard.
Create Webhook SubscriptionTool to create a new webhook subscription.
Delete CompanyTool to delete a specific company.
Delete Company FieldTool to delete a specific company custom field.
Delete Custom Field ValueTool to delete a custom field value from a hierarchy entity in Productboard.
Delete Entity RelationshipTool to delete a relationship between two entities.
Delete Entity V2Tool to delete a PM entity using the v2 API.
Delete FeatureTool to delete a specific feature.
Delete Feature Objective LinkTool to delete a link between a feature and an objective.
Delete InitiativeTool to delete a specific initiative.
Delete Key ResultTool to delete a specific key result from Productboard.
Delete Note RelationshipTool to delete a note relationship.
Delete Note V2Tool to delete a note using the v2 API.
Delete Note TagTool to remove a tag from a Productboard note.
Delete ObjectiveTool to delete a specific objective from Productboard.
Delete Objective-Feature LinkTool to delete a link between an objective and a feature.
Delete ReleaseTool to delete a specific release.
Delete UserTool to delete a specific user.
Delete Webhook SubscriptionTool to delete a webhook subscription.
Get ComponentTool to retrieve details of a specific component.
Get Custom Field ValueTool to retrieve a custom field's value for a specific hierarchy entity.
Get Entity ConfigurationTool to retrieve entity configuration for a specific type.
Get Entity V2Tool to retrieve a PM entity using the v2 API.
Get Feature Release AssignmentTool to retrieve a specific feature release assignment.
Get Hierarchy Entity Custom FieldTool to retrieve a specific custom field definition for hierarchy entities.
Get Notes Configuration V2Tool to retrieve note configuration by type (simple, conversation, or opportunity).
Get Note V2Tool to retrieve a note using the v2 API.
Get ObjectiveTool to retrieve details of a specific objective.
Get ReleaseTool to retrieve details of a specific release by ID.
Get Release GroupTool to retrieve details of a specific release group.
Get Webhook SubscriptionTool to retrieve details of a specific webhook subscription.
List Analytics Member Activities V2Tool to retrieve member activity analytics data from Productboard.
List CompaniesTool to list companies.
List Company Custom FieldsLists all custom field definitions for companies in your Productboard workspace.
List Custom FieldsLists custom field definitions for hierarchy entities (Products, Components, Features).
List Custom Field ValuesLists custom field values for hierarchy entities (products, components, features) in Productboard.
List Entities Configurations V2Tool to retrieve configurations for all entity types in Productboard.
List Entity RelationshipsTool to retrieve relationships for an entity in Productboard.
List Entities V2Tool to list entities from Productboard using the v2 API.
List Feature InitiativesTool to list initiatives linked to a given feature.
List Feature ObjectivesLists all objectives (OKRs) linked to a top-level feature.
List Feature Release AssignmentsTool to list feature–release assignments.
List Feature StatusesTool to list feature statuses.
List Feedback Form ConfigurationsTool to list feedback form configurations.
List InitiativesTool to list initiatives from Productboard.
List Jira IntegrationsTool to list Jira integrations.
List Key ResultsList key results from Productboard.
List Notes Configurations V2Tool to list note configurations from Productboard v2 API.
List Note LinksTool to list links associated with a note.
List Note Relationships V2Tool to retrieve relationships associated with a note.
List Notes V2Tool to retrieve a paginated list of notes from Productboard using the v2 API.
List Note TagsTool to retrieve all tags associated with a specific Productboard note.
List Objective Linked FeaturesLists all features linked to a specific objective.
List Objective Linked InitiativesTool to list initiatives linked to a specific objective.
List Plugin IntegrationsList all plugin integrations in the Productboard workspace.
List Release GroupsLists all release groups in the Productboard workspace.
List ReleasesTool to list all releases in Productboard.
List UsersRetrieves a paginated list of all users in the Productboard workspace.
List Webhook SubscriptionsTool to list all webhook subscriptions.
Remove Note FollowerTool to remove a follower from a Productboard note.
Retrieve CompanyTool to retrieve details of a specific company.
Retrieve Company FieldTool to retrieve details of a specific company custom field.
Retrieve Company Field ValueTool to retrieve a specific company custom field value.
Retrieve FeatureTool to retrieve details of a specific feature.
Retrieve ProductTool to retrieve details of a specific product.
Retrieve UserTool to retrieve details of a specific user.
List SCIM UsersTool to list users via SCIM.
Search Entities V2Tool to search for entities across Productboard using the v2 API.
Set Company Field ValueTool to set or replace a specific company custom field's value.
Set Custom Field ValueTool to set a custom field value on a hierarchy entity.
Set Entity Parent RelationshipTool to set parent relationship on an entity.
Set Feature Release AssignmentTool to update a feature release assignment.
Set FeaturesTool to update a feature by ID.
Set Note Customer RelationshipTool to set a customer relationship on a note in Productboard.
Set ProductTool to update a product using PUT method in Productboard.
Update Company Custom FieldTool to update a company custom field name.
Update CompanyTool to update an existing company in Productboard.
Update ComponentTool to update an existing component.
Update Entity V2Tool to update a PM entity using the v2 API.
Update FeaturesTool to update a feature in Productboard.
Update Note V2Tool to update a note using the v2 API.
Update ObjectiveTool to update an existing objective in Productboard.
Update ProductTool to update a product in Productboard.
Update ReleaseTool to update an existing release in Productboard.
Update UserTool to update a user's information.

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: ["productboard"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Productboard 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 Productboard-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 Productboard 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 productboard, 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 Productboard 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 Productboard 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: ["productboard"],
  });

  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 productboard, 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 Productboard 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 Productboard MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Productboard MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Productboard MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Productboard MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Productboard MCP with Claude Cowork

Codex logo

Codex

Use Productboard MCP with Codex

OpenClaw logo

OpenClaw

Use Productboard MCP with OpenClaw

Hermes logo

Hermes

Use Productboard MCP with Hermes

CLI logo

CLI

Use Productboard MCP with CLI

Google ADK logo

Google ADK

Use Productboard MCP with Google ADK

LangChain logo

LangChain

Use Productboard MCP with LangChain

Mastra AI logo

Mastra AI

Use Productboard MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Productboard MCP with LlamaIndex

CrewAI logo

CrewAI

Use Productboard MCP with CrewAI

FAQ

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

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

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

Yes, absolutely. You can configure which Productboard 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 Productboard 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↗