# How to integrate Mailtrap MCP with Vercel AI SDK v6

```json
{
  "title": "How to integrate Mailtrap MCP with Vercel AI SDK v6",
  "toolkit": "Mailtrap",
  "toolkit_slug": "mailtrap",
  "framework": "Vercel AI SDK",
  "framework_slug": "ai-sdk",
  "url": "https://composio.dev/toolkits/mailtrap/framework/ai-sdk",
  "markdown_url": "https://composio.dev/toolkits/mailtrap/framework/ai-sdk.md",
  "updated_at": "2026-03-29T06:41:28.798Z"
}
```

## Introduction

This guide walks you through connecting Mailtrap to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Mailtrap agent that can send a test email to marketing team, list all emails sent from mailtrap today, create a new inbox for transactional testing through natural language commands.
This guide will help you understand how to give your Vercel AI SDK agent real control over a Mailtrap account through Composio's Mailtrap MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Mailtrap with

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

## TL;DR

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

The Mailtrap MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mailtrap account. It provides structured and secure access so your agent can perform Mailtrap operations on your behalf.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `MAILTRAP_CLEAN_INBOX` | Clean Inbox | Tool to clean an inbox in Mailtrap by deleting all messages. Use when you need to remove all emails from an inbox while keeping the inbox itself. |
| `MAILTRAP_CREATE_CONTACT` | Create Contact | Tool to create a new contact in Mailtrap. Use when you need to add a contact with an email address to a Mailtrap account. Optionally include custom fields and assign to contact lists. |
| `MAILTRAP_CREATE_CONTACT_EVENT` | Create Contact Event | Tool to create a contact event in Mailtrap. Use when you need to track custom events associated with a contact for segmentation or automation triggers. |
| `MAILTRAP_CREATE_CONTACT_EXPORT` | Create Contact Export | Tool to create a contact export job for a Mailtrap account. Use when you need to export contacts with filters. The export is processed asynchronously - the response includes a job ID and status. Check the status field; when it becomes 'finished', the url field will contain the download link for the exported contacts file. Filters are required - you must specify at least one filter such as subscription_status (subscribed/unsubscribed) or list_id (array of list IDs). |
| `MAILTRAP_CREATE_CONTACT_FIELD` | Create Contact Field | Tool to create a custom contact field in Mailtrap. Use when you need to add new contact attributes for personalization and segmentation in email campaigns. |
| `MAILTRAP_CREATE_CONTACT_LIST` | Create Contact List | Tool to create a new contact list in Mailtrap. Use when you need to organize contacts into groups or segments. Each contact list has a unique ID and name that can be used to add contacts to it later. |
| `MAILTRAP_CREATE_EMAIL_TEMPLATE` | Create Email Template | Tool to create a new email template in Mailtrap account. Use when you need to create a reusable email template with HTML/text content, subject, and category. The template can be used for sending promotional, transactional, or newsletter emails. |
| `MAILTRAP_CREATE_SENDING_DOMAIN` | Create Sending Domain | Tool to create a new sending domain in Mailtrap. Use when you need to register a domain for sending transactional emails. After creation, DNS records must be configured before the domain can be used for sending. |
| `MAILTRAP_DELETE_CONTACT` | Delete Contact | Tool to delete a contact from a Mailtrap account. Use when you need to permanently remove a contact by their UUID or email address. The deletion is permanent and cannot be undone. |
| `MAILTRAP_DELETE_CONTACT_FIELD` | Delete Contact Field | Tool to delete a contact field by its ID. Use when you need to remove a custom contact field from an account. |
| `MAILTRAP_DELETE_CONTACT_LIST` | Delete Contact List | Tool to delete a contact list by its ID. Use when you need to remove a contact list from an account. |
| `MAILTRAP_DELETE_EMAIL_TEMPLATE` | Delete Email Template | Tool to delete an email template from a Mailtrap account. Use when you need to remove an existing email template. |
| `MAILTRAP_DELETE_PROJECT` | Delete Project | Tool to delete a project from Mailtrap. Use when you need to permanently remove a project and its associated resources. Returns the ID of the deleted project. |
| `MAILTRAP_DELETE_SENDING_DOMAIN` | Delete Sending Domain | Tool to delete a sending domain from a Mailtrap account. Use when you need to remove a domain permanently. |
| `MAILTRAP_GET_BILLING_USAGE` | Get Billing Usage | Tool to retrieve current billing cycle usage for an account. Use when you need to check billing information, usage limits, or consumption for Email Sandbox and Email Sending services. |
| `MAILTRAP_GET_CONTACT` | Get Contact | Tool to retrieve a contact by UUID or email address from Mailtrap. Use when you need to fetch details of a specific contact including their subscription status, lists, and custom fields. |
| `MAILTRAP_GET_CONTACT_EXPORT` | Get Contact Export | Tool to retrieve the status of a contact export. Use when you need to check the progress of an export or download the exported contacts file. |
| `MAILTRAP_GET_CONTACT_FIELD` | Get Contact Field | Tool to retrieve contact field details by field ID. Use when you need to get information about a specific custom field in your contacts. |
| `MAILTRAP_GET_CONTACT_IMPORT_STATUS` | Get Contact Import Status | Tool to retrieve the status of a contact import operation. Use when you need to check the progress or completion status of a contact import. Use after initiating a contact import to monitor its status and retrieve statistics once finished. |
| `MAILTRAP_GET_CONTACT_LIST` | Get Contact List | Tool to retrieve a specific contact list by its ID. Use when you need to fetch details about a contact list in a Mailtrap account. |
| `MAILTRAP_GET_EMAIL_TEMPLATE` | Get Email Template | Tool to retrieve details of a specific email template by ID. Use when you need to fetch template content, metadata, or configuration for an existing email template. |
| `MAILTRAP_GET_INBOX_ATTRIBUTES` | Get Inbox Attributes | Tool to retrieve inbox attributes from Mailtrap. Use when you need to get details about a specific inbox including its configuration, statistics, and permissions. |
| `MAILTRAP_GET_MESSAGE_HTML_BODY` | Get Message HTML Body | Tool to retrieve the HTML body of a message from Mailtrap. Use when you need to get the formatted HTML content of a specific email message. |
| `MAILTRAP_GET_PERMISSION_RESOURCES` | Get Permission Resources | Tool to retrieve all resources in account for permission management. Use when you need to see the hierarchical structure of projects, inboxes, and other resources with their access levels for the current authentication token. |
| `MAILTRAP_GET_PROJECT_BY_ID` | Get Project by ID | Tool to retrieve project details from Mailtrap by project ID. Use when you need to get information about a specific project including its inboxes, permissions, and share links. |
| `MAILTRAP_GET_SENDING_DOMAIN` | Get Sending Domain | Tool to retrieve sending domain details from Mailtrap. Use when you need to check domain configuration, DNS verification status, or tracking settings. |
| `MAILTRAP_GET_SENDING_STATS` | Get Sending Stats | Tool to retrieve email sending statistics from Mailtrap for a specific account. Use when you need metrics like delivery rate, bounce rate, open rate, click rate, and spam rate for a date range. |
| `MAILTRAP_GET_SENDING_STATS_BY_CATEGORIES` | Get Sending Stats by Categories | Tool to retrieve email sending statistics grouped by categories. Use when you need to analyze email performance metrics (delivery, bounce, open, click, spam rates) segmented by email categories within a date range. |
| `MAILTRAP_GET_SENDING_STATS_BY_DATE` | Get Sending Stats by Date | Tool to retrieve email sending statistics aggregated by date. Use when you need to analyze email delivery performance, bounce rates, open rates, click rates, and spam rates for a specific date range. |
| `MAILTRAP_GET_SENDING_STATS_BY_DOMAINS` | Get Sending Stats by Domains | Tool to retrieve sending statistics grouped by domains for a Mailtrap account. Use when you need email delivery, bounce, open, click, and spam metrics broken down by sending domain for a specific date range. Supports filtering by domain IDs, sending streams, categories, and email service providers. |
| `MAILTRAP_GET_SENDING_STATS_BY_ESP` | Get Sending Stats by ESP | Tool to retrieve email sending statistics grouped by email service providers (ESPs) for a specified date range. Returns delivery, bounce, open, click, and spam metrics for each ESP. Use when you need to analyze email performance across different email providers like Google, Yahoo, Microsoft, etc. |
| `MAILTRAP_IMPORT_CONTACTS` | Import Contacts | Tool to import contacts in bulk to Mailtrap. Use when you need to add or update multiple contacts at once. The import operation is asynchronous and returns a job ID that can be used to check the status later. |
| `MAILTRAP_LIST_ACCOUNTS` | List Accounts | Tool to list all Mailtrap accounts you have access to. Use when you need to retrieve account information or get account IDs for other operations. Returns account ID, name, and access levels (1000=owner, 100=admin, 10=viewer). |
| `MAILTRAP_LIST_CONTACT_FIELDS` | List Contact Fields | Tool to get all contact fields for a Mailtrap account. Use when you need to retrieve custom field definitions for contacts. |
| `MAILTRAP_LIST_CONTACT_LISTS` | List Contact Lists | Tool to retrieve all contact lists for a Mailtrap account. Use when you need to view available contact lists or obtain contact list IDs for other operations. |
| `MAILTRAP_LIST_EMAIL_TEMPLATES` | List Email Templates | Tool to retrieve all email templates for a Mailtrap account. Use when you need to list available templates, browse template configurations, or find a specific template by name or attributes. |
| `MAILTRAP_LIST_INBOXES` | List Inboxes | Tool to get a list of inboxes for a Mailtrap account. Use when you need to retrieve all inboxes associated with an account ID. Returns the list of inboxes with their configuration, permissions, and statistics. |
| `MAILTRAP_LIST_MESSAGES_IN_INBOX` | List Messages in Inbox | Tool to get messages from a Mailtrap inbox. Use when you need to retrieve emails from a specific inbox, with support for search filtering and pagination. Returns up to 30 messages per request. |
| `MAILTRAP_LIST_PROJECTS` | List Projects | Tool to get a list of projects for a Mailtrap account. Use when you need to retrieve all projects and their associated inboxes for a specific account. Returns project attributes, permissions, and nested inbox information. |
| `MAILTRAP_LIST_SENDING_DOMAINS` | List Sending Domains | Tool to list all sending domains for a Mailtrap account. Use when you need to retrieve configured domains for email sending. |
| `MAILTRAP_LIST_EMAIL_SUPPRESSIONS` | List Email Suppressions | Tool to list suppressed email addresses for a Mailtrap account. Use when you need to view which emails are blocked from receiving messages due to bounces, complaints, unsubscribes, or manual suppression. |
| `MAILTRAP_MARK_INBOX_AS_READ` | Mark Inbox as Read | Tool to mark all messages in a Mailtrap inbox as read. Use when you need to mark all unread messages as read in a specific inbox. |
| `MAILTRAP_RESET_INBOX_CREDENTIALS` | Reset Inbox Credentials | Tool to reset SMTP credentials for a Mailtrap inbox. Use when you need to regenerate the username and password for inbox access. |
| `MAILTRAP_UPDATE_CONTACT` | Update contact | Tool to update an existing contact in Mailtrap. Use when you need to modify contact details such as email, custom fields, list memberships, or subscription status. If the contact doesn't exist, it will be created. |
| `MAILTRAP_UPDATE_CONTACT_FIELD` | Update Contact Field | Tool to update a contact field in Mailtrap. Use when you need to modify the name or merge tag of an existing contact field. |
| `MAILTRAP_UPDATE_CONTACT_LIST` | Update Contact List | Tool to update a contact list's name in Mailtrap. Use when you need to rename an existing contact list. |
| `MAILTRAP_UPDATE_EMAIL_TEMPLATE` | Update Email Template | Tool to update an existing email template in Mailtrap account. Use when you need to modify template properties such as name, subject, category, HTML body, or plain text body. All fields in the email_template object are optional - only provide the fields you want to update. |
| `MAILTRAP_UPDATE_INBOX` | Update inbox | Tool to update an inbox's settings in Mailtrap. Use when you need to change the inbox name or email username. |
| `MAILTRAP_UPDATE_PROJECT` | Update project | Tool to update a project's name in Mailtrap. Use when you need to rename an existing project. |

## Supported Triggers

None listed.

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

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

## Step-by-step Guide

### 1. Prerequisites

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

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

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

### 2. Install required dependencies

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

### 3. Set up environment variables

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

### 4. Import required modules and validate environment

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

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

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

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

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

What's happening:
- We're creating a Tool Router session that gives your agent access to Mailtrap 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 Mailtrap-related tools through the MCP protocol
```typescript
async function main() {
  // Create a tool router session for the user
  const session = await composio.create(composioUserID!, {
    toolkits: ["mailtrap"],
  });

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

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

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

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

### 7. Initialize conversation and CLI interface

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

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

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

rl.prompt();
```

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

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

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

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

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

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

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

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

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

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

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

## Complete Code

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

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

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

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

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

  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 mailtrap, 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 Mailtrap 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 Mailtrap MCP Agent with another framework

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

## Related Toolkits

- [Google Sheets](https://composio.dev/toolkits/googlesheets) - 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](https://composio.dev/toolkits/notion) - Notion is a collaborative workspace for notes, docs, wikis, and tasks. It streamlines team knowledge, project tracking, and workflow customization in one place.
- [Airtable](https://composio.dev/toolkits/airtable) - 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.
- [Asana](https://composio.dev/toolkits/asana) - Asana is a collaborative work management platform for teams to organize and track projects. It streamlines teamwork, boosts productivity, and keeps everyone aligned on goals.
- [Google Tasks](https://composio.dev/toolkits/googletasks) - Google Tasks is a to-do list and task management tool integrated into Gmail and Google Calendar. It helps you organize, track, and complete tasks across your Google ecosystem.
- [Linear](https://composio.dev/toolkits/linear) - Linear is a modern issue tracking and project planning tool for fast-moving teams. It helps streamline workflows, organize projects, and boost productivity.
- [Jira](https://composio.dev/toolkits/jira) - Jira is Atlassian’s platform for bug tracking, issue tracking, and agile project management. It helps teams organize work, prioritize tasks, and deliver projects efficiently.
- [Clickup](https://composio.dev/toolkits/clickup) - ClickUp is an all-in-one productivity platform for managing tasks, docs, goals, and team collaboration. It streamlines project workflows so teams can work smarter and stay organized in one place.
- [Monday](https://composio.dev/toolkits/monday) - Monday.com is a customizable work management platform for project planning and collaboration. It helps teams organize tasks, automate workflows, and track progress in real time.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agiled](https://composio.dev/toolkits/agiled) - Agiled is an all-in-one business management platform for CRM, projects, and finance. It helps you streamline workflows, consolidate client data, and manage business processes in one place.
- [Ascora](https://composio.dev/toolkits/ascora) - Ascora is a cloud-based field service management platform for service businesses. It streamlines scheduling, invoicing, and customer operations in one place.
- [Basecamp](https://composio.dev/toolkits/basecamp) - Basecamp is a project management and team collaboration tool by 37signals. It helps teams organize tasks, share files, and communicate efficiently in one place.
- [Beeminder](https://composio.dev/toolkits/beeminder) - Beeminder is an online goal-tracking platform that uses monetary pledges to keep you motivated. Stay accountable and hit your targets with real financial incentives.
- [Boxhero](https://composio.dev/toolkits/boxhero) - Boxhero is a cloud-based inventory management platform for SMBs, offering real-time updates, barcode scanning, and team collaboration. It helps businesses streamline stock tracking and analytics for smarter inventory decisions.
- [Breathe HR](https://composio.dev/toolkits/breathehr) - Breathe HR is cloud-based HR software for SMEs to manage employee data, absences, and performance. It simplifies HR admin, making it easy to keep employee records accurate and up to date.
- [Breeze](https://composio.dev/toolkits/breeze) - Breeze is a project management platform designed to help teams plan, track, and collaborate on projects. It streamlines workflows and keeps everyone on the same page.
- [Bugherd](https://composio.dev/toolkits/bugherd) - Bugherd is a visual feedback and bug tracking tool for websites. It helps teams and clients report website issues directly on live sites for faster fixes.
- [Canny](https://composio.dev/toolkits/canny) - Canny is a platform for managing customer feedback and feature requests. It helps teams prioritize product decisions based on real user insights.
- [Chmeetings](https://composio.dev/toolkits/chmeetings) - Chmeetings is a church management platform for events, members, donations, and volunteers. It streamlines church operations and improves community engagement.

## Frequently Asked Questions

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

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

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

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

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