Rocketlane with Vercel AI SDK

How to integrate Rocketlane MCP with Vercel AI SDK v6

Trusted by

GET STARTED FOR FREE GET A DEMO

30 min · no commitment · see it on your stack

Introduction Also integrate Rocketlane with TL;DR What is Vercel AI SDK What is the Rocketlane MCP server Supported Tools & Triggers Creating MCP Server - Stand-alone vs Composio SDK Step-by-step Guide Complete Code Conclusion How to build Rocketlane MCP Agent with another framework Explore Other Toolkits FAQ

Connect Rocketlane without Auth hassles

We manage OAuth, API Key, token refresh, and scopes, you just build.

Try for Free

Introduction

This guide walks you through connecting Rocketlane to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Rocketlane agent that can create a new onboarding project for acme corp, log two hours to client implementation task, archive completed projects from last quarter through natural language commands.

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

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

Also integrate Rocketlane with

OpenAI Agents SDK Claude Agent SDK Claude Code Claude Cowork Codex OpenClaw Hermes CLI Google ADK LangChain Mastra AI LlamaIndex CrewAI

TL;DR

Here's what you'll learn:

How to set up and configure a Vercel AI SDK agent with Rocketlane integration
Using Composio's Tool Router to dynamically load and access Rocketlane 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 Rocketlane MCP server, and what's possible with it?

The Rocketlane MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Rocketlane account. It provides structured and secure access to your onboarding projects, tasks, and customer data, so your agent can perform actions like creating tasks, managing companies, tracking time entries, and handling project organization on your behalf.

Project and company management: Easily direct your agent to create new projects or companies, retrieve detailed company info, and keep your workspace organized.
Task creation and deletion: Have your agent add new tasks to any project or swiftly delete outdated tasks using their unique identifiers.
Time entry tracking: Log time spent on tasks or projects, review details, or delete time entries for accurate billing and reporting.
Custom field insights: Retrieve all available custom fields or fetch specific field details to tailor onboarding workflows to your needs.
Project archiving and cleanup: Archive completed projects for future reference or permanently delete projects when they're no longer needed, keeping your workspace tidy.

Supported Tools & Triggers

Tools

Add Assignee To TaskAdd assignees to a task by task ID.

Add Field OptionTool to add a new option to a SINGLE_CHOICE or MULTIPLE_CHOICE field.

Add Followers To TaskTool to add followers to a task by Id.

Add Members to ProjectTool to add team members to a project using the projectId.

Add Members to ConversationAdd members to a conversation in Rocketlane.

Archive Project by IDArchives a specific project based on its unique identifier.

Create CommentTool to create a comment in Rocketlane.

Create CompanyCreates a new company (account) in Rocketlane.

Create ConversationCreates a new conversation in Rocketlane.

Create FieldTool to create a custom field in Rocketlane.

Create PhaseTool to create a new phase in a Rocketlane project.

Create ProjectTool to create a new project in Rocketlane.

Create SpaceCreates a new space for a given project in Rocketlane.

Create Space DocumentTool to create a new space document in Rocketlane.

Create TaskCreates a new task.

Create Time EntryTool to create a new time entry in Rocketlane.

Delete Comment By IDTool to delete a comment by its ID.

Delete ConversationTool to delete a conversation by its unique identifier.

Delete FieldTool to permanently delete a custom field using its unique identifier.

Delete PhasePermanently delete a phase from the project using its unique identifier (phaseId).

Delete ProjectThis tool allows users to permanently delete a project in Rocketlane.

Delete SpaceTool to permanently delete a space from a project by its ID.

Delete Space DocumentTool to permanently delete a space document by its ID.

Delete Task By IDDelete a specific task using its unique identifier (taskId).

Delete Time Entry by IDDelete a specific time entry using its unique identifier (timeEntryId).

Get All ConversationsTool to retrieve all conversations in Rocketlane.

Get All FieldsRetrieve all custom fields available in the system.

Get All Resource AllocationsTool to retrieve all resource allocations from Rocketlane.

Get All SpacesTool to retrieve all spaces for a specific project in Rocketlane.

Get All TasksTool to retrieve all tasks from Rocketlane with advanced filtering options.

Get All Time-OffsTool to retrieve all time-offs from Rocketlane with advanced filtering options.

Get CommentsTool to retrieve all comments from Rocketlane.

Get CompanyThis tool retrieves detailed information about a specific company/account in Rocketlane by its ID.

Get ConversationTool to retrieve detailed information about a conversation by its ID.

Get Field By IDRetrieve detailed information about a specific custom field using its unique identifier (fieldId).

Get Phase by IDTool to retrieve extensive information about a specific phase by its unique identifier.

Get Project by IDRetrieves detailed information about a specific project using its unique identifier.

Get Space by IDTool to retrieve detailed information about a specific space using its unique identifier.

Get Task By IdRetrieve extensive information about a specific task using the task's unique identifier (taskId).

Get Template By IDRetrieve detailed information about a specific template using its unique identifier (templateId).

Get Time EntriesTool to retrieve all time entries from Rocketlane.

Get Time Entry By IDRetrieve detailed information about a specific time entry using its unique identifier (timeEntryId).

Get Time Entry CategoriesTool to retrieve time entry categories from Rocketlane.

Get User By IDRetrieve detailed information about a specific user using their unique identifier (userId).

List CompaniesThis tool retrieves a list of all companies/accounts in Rocketlane.

List CurrenciesReturns a predefined list of commonly used currencies since Rocketlane API doesn't provide a dedicated currencies endpoint.

List Project PhasesThis tool retrieves a list of project phases from Rocketlane.

List ProjectsThis tool retrieves a list of all projects in the Rocketlane instance.

List TemplatesThis tool retrieves a list of all available templates in Rocketlane.

List UsersThis tool retrieves all users in the Rocketlane instance.

Move Task To Given PhaseTool to move a task to a different phase by task ID and phase ID.

Remove Assignees From TaskTool to remove assignees from a task by its unique identifier.

Remove Dependencies From TaskTool to remove dependencies from a task by ID.

Remove Followers From TaskTool to remove followers from a task by task ID.

Remove Members from ConversationRemove members from a conversation in Rocketlane.

Retrieve Subscription DetailsRetrieves detailed information about the current subscription.

Search InvoicesTool to retrieve all invoices from Rocketlane.

Search Time EntriesTool to search time entries with filters in Rocketlane.

Search User By EmailSearch User By Email Id.

Update CompanyThis tool updates an existing company/account in Rocketlane.

Update ConversationTool to update an existing conversation in Rocketlane by its ID.

Update FieldTool to update field information by ID.

Update Field OptionTool to update an existing option's label and color in a SINGLE_CHOICE or MULTIPLE_CHOICE field.

Update PhaseTool to update phase information by phase ID.

Update Project By IdUpdates an existing project's details using its unique identifier.

Update SpaceTool to update space details by its unique identifier.

Update Space DocumentTool to update a space document's properties by its unique identifier in Rocketlane.

Update Task by IDTool to update task details by ID.

Update Time Entry by IDUpdate existing time entry details using its unique identifier (timeEntryId).

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:

Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
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: ["rocketlane"],
  });

  const mcpUrl = session.mcp.url;

What's happening:

We're creating a Tool Router session that gives your agent access to Rocketlane 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 Rocketlane-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 Rocketlane 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 rocketlane, 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 Rocketlane 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 Rocketlane 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: ["rocketlane"],
  });

  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 rocketlane, 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 Rocketlane 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 Rocketlane MCP Agent with another framework

OpenAI Agents SDK

Use Rocketlane MCP with OpenAI Agents SDK

Claude Agent SDK

Use Rocketlane MCP with Claude Agent SDK

Claude Code

Use Rocketlane MCP with Claude Code

Claude Cowork

Use Rocketlane MCP with Claude Cowork

Codex

Use Rocketlane MCP with Codex

OpenClaw

Use Rocketlane MCP with OpenClaw

Hermes

Use Rocketlane MCP with Hermes

CLI

Use Rocketlane MCP with CLI

Google ADK

Use Rocketlane MCP with Google ADK

LangChain

Use Rocketlane MCP with LangChain

Mastra AI

Use Rocketlane MCP with Mastra AI

LlamaIndex

Use Rocketlane MCP with LlamaIndex

CrewAI

Use Rocketlane MCP with CrewAI

Explore Other Toolkits

Google Sheets

Oauth2

Google Sheets is a cloud-based spreadsheet tool for real-time collaboration and data analysis. It lets teams work together from anywhere, updating information instantly.

Notion

Oauth2Api Key

Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.

Airtable

Oauth2Api Key

Airtable combines the flexibility of spreadsheets with the power of a database for easy project and data management. Teams use Airtable to organize, track, and collaborate with custom views and automations.

TOOLKIT MARKETPLACE

FAQ

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

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

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

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

Used by agents from

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 free Get a demo↗

Harsha GaddipatiCo-founder, Slashy

Karan skipped his own birthday party to fix our critical issue. It was 10 pm and he diverted his Waymo to help us instead. This really sets the bar, shows you the commitment you need to have when users rely on your software.

Abhi AryaCo-founder, Opennote

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it has immensely helped in keeping new users on the platform.

Nirman DaveCEO, Zams

We chose Composio over Pipedream because it delivered depth where it mattered. It supported niche tools and tricky edge cases that other platforms simply ignored. Giving us confidence to scale without compromising.

Ryan YuFounder, Extra Thursday

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down in the complexities of managing agent auth would have been a death sentence for Extra Thursday.

Tomisin JenrolaFounder & CEO, SwarmZero

Before partnering with Composio, adding tool integrations was a slow, resource-intensive process. Each integration could take weeks or months of engineering time, and maintaining them meant constantly keeping up with API changes.

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Harsha GaddipatiCo-founder, Slashy

Abhi AryaCo-founder, Opennote

Nirman DaveCEO, Zams

Ryan YuFounder, Extra Thursday

Tomisin JenrolaFounder & CEO, SwarmZero

Jerome LeclancheCo-Founder, Ingram Technologies

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

How to integrate Rocketlane MCP with Vercel AI SDK v6

Table of Contents

Connect Rocketlane without Auth hassles

Introduction

Also integrate Rocketlane with

TL;DR

What is Vercel AI SDK?

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

Supported Tools & Triggers

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

What is Composio SDK?

How the Composio SDK works

Step-by-step Guide

Prerequisites

Getting API Keys for OpenAI and Composio

Install required dependencies

Set up environment variables

Import required modules and validate environment

Create Tool Router session and initialize MCP client

Connect to MCP server and retrieve tools

Initialize conversation and CLI interface

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

Complete Code

Conclusion

How to build Rocketlane MCP Agent with another framework

OpenAI Agents SDK

Claude Agent SDK

Claude Code

Claude Cowork

Codex

OpenClaw

Hermes

CLI

Google ADK

LangChain

Mastra AI

LlamaIndex

CrewAI

Explore Other Toolkits

Google Sheets

Notion

Airtable

FAQ

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

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

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

How safe is my data with Composio Tool Router?

Used by agents from

Never worry about agent reliability