How to integrate Missive MCP with Vercel AI SDK v6

This guide walks you through connecting Missive to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Missive agent that can list all team members for marketing, create a draft email for client follow-up, send a chat message in project conversation through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Missive account through Composio's Missive MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Missive logoMissive
Api Key

Missive is a collaborative email and chat app for teams to manage conversations and tasks together. It helps streamline team inboxes, shared labels, and internal discussion in one place.

40 Tools

Introduction

This guide walks you through connecting Missive to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Missive agent that can list all team members for marketing, create a draft email for client follow-up, send a chat message in project conversation through natural language commands.

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

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

Also integrate Missive with

TL;DR

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

The Missive MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Missive account. It provides structured and secure access to your team's shared inboxes and chat threads, so your agent can perform actions like drafting emails, sending messages, generating reports, and managing team communication on your behalf.

  • Automated message drafting and scheduling: Let your agent create and save email, SMS, WhatsApp, or live chat drafts for later editing or scheduled sending.
  • Instant message sending in conversations: Have your agent send new messages directly to any Missive conversation, keeping your team in the loop in real time.
  • Team and user management: Effortlessly list all teams and their members, or pull a full directory of users in your Missive organization for easy coordination and task assignment.
  • Analytics report generation: Direct your agent to create detailed analytics reports across time ranges and filters, helping your team track productivity and engagement.
  • Webhook automation setup: Enable your agent to create or delete webhook subscriptions, so you can automate notifications and integrations with other tools as needed.

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

Step by step09 STEPS
1

Prerequisites

Before you begin, make sure you have:
  • Node.js and npm installed
  • A Composio account with API key
  • An OpenAI API key
2

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.
3

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
4

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
5

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
6

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: ["missive"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Missive 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 Missive-related tools through the MCP protocol
7

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 Missive tools that the agent can use
8

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 missive, 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
9

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 Missive 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 Missive 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: ["missive"],
  });

  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 missive, 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 Missive 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.
TOOLS

Supported Tools

Every Missive action and event your agent gets out of the box.

Create Analytics Report

Tool to create an analytics report.

Create Missive Contacts

Tool to create one or more contacts in a Missive contact book.

Create Draft

Tool to create a new draft in Missive.

Create Missive Post

Tool to create a post in a Missive conversation.

Create Canned Response

Tool to create one or more canned responses (templates) in Missive.

Create Shared Label

Tool to create one or more shared labels at the organization level.

Create Missive Task

Tool to create a task in Missive.

Create Team

Tool to create a new team in an organization.

Create Webhook

Tool to create a webhook subscription.

Delete Draft

Tool to delete a draft from a conversation by draft ID.

Delete Post

Tool to delete a post from a conversation by post ID.

Delete Saved Responses

Tool to delete one or more saved responses by ID.

Delete Webhook

Tool to delete a webhook subscription by webhook ID.

Get Analytics Report

Tool to fetch a completed analytics report using its ID.

Get Missive Contact

Tool to fetch a specific contact using the contact ID.

Get Missive Conversation

Tool to fetch full conversation metadata (assignees/users/labels/team/org) for a specific conversation ID.

List Conversation Messages

Tool to list messages belonging to a Missive conversation (newest first).

Get Missive Message

Tool to fetch full message details including headers, HTML body, and attachments.

Get Missive Response

Tool to fetch a specific saved response using the response ID.

Get Missive Task

Tool to get a single task by ID with full details including assignees, team, and conversation info.

List Missive Contact Books

Tool to list contact books the authenticated user has access to.

List Missive Contact Groups

Tool to list contact groups or organizations linked to a contact book.

List Missive Contacts

Tool to list contacts from a contact book.

List Conversation Comments

Tool to list comments in a Missive conversation ordered from newest to oldest.

List Conversation Drafts

Tool to list draft messages in a Missive conversation (newest first).

List Conversation Posts

Tool to list posts in a Missive conversation ordered by newest first.

List Missive Conversations

Tool to list conversations visible to the authenticated user ordered by newest activity first.

List Messages by Message-ID

Tool to fetch messages matching an email Message-ID header.

List Missive Organizations

Tool to list organizations the authenticated user is part of.

List Missive Saved Responses

Tool to list saved responses (canned responses/templates) for the authenticated user.

List Missive Shared Labels

Tool to list shared labels (organization-level labels) available to the authenticated user.

List Missive Tasks

Tool to list tasks accessible to the authenticated user.

List Missive Teams

Tool to list all teams.

List Missive Users

Tool to list all users.

Merge Missive Conversations

Tool to merge multiple conversations into one.

Update Missive Contact

Tool to update one or more contacts in Missive.

Update Saved Response

Tool to update one or more saved responses in Missive.

Update Shared Labels

Tool to update one or more shared labels in Missive.

Update Missive Task

Tool to update an existing task's attributes in Missive.

Update Missive Team

Tool to update one or more teams in Missive.

FAQ

Frequently asked questions

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

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 Missive tools.

Yes, absolutely. You can configure which Missive 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.

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 Missive data and credentials are handled as safely as possible.

Start with Missive.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Missive tool your agent needs.Free to start.

Start building