# How to integrate Insighto ai MCP with Vercel AI SDK v6

```json
{
  "title": "How to integrate Insighto ai MCP with Vercel AI SDK v6",
  "toolkit": "Insighto ai",
  "toolkit_slug": "insighto_ai",
  "framework": "Vercel AI SDK",
  "framework_slug": "ai-sdk",
  "url": "https://composio.dev/toolkits/insighto_ai/framework/ai-sdk",
  "markdown_url": "https://composio.dev/toolkits/insighto_ai/framework/ai-sdk.md",
  "updated_at": "2026-05-12T10:15:55.491Z"
}
```

## Introduction

This guide walks you through connecting Insighto ai to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Insighto ai agent that can send whatsapp message to all new leads, fetch conversation history for a specific contact, list all available chatbot intents today through natural language commands.
This guide will help you understand how to give your Vercel AI SDK agent real control over a Insighto ai account through Composio's Insighto ai MCP server.
Before we dive in, let's take a quick look at the key ideas and tools involved.

## Also integrate Insighto ai with

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

## TL;DR

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

The Insighto ai MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Insighto ai account. It provides structured and secure access to your conversational AI assets, so your agent can create new intents, manage contacts, analyze conversations, deploy widgets, and broadcast messages across channels on your behalf.
- Intent creation and management: Easily add or review conversational intents to enhance your chatbots and voice agents, making them smarter and more responsive.
- Bulk contact communication: Let your agent send messages to multiple contacts in bulk through WhatsApp or SMS, enabling efficient campaign blasts and customer updates.
- Comprehensive contact and conversation insights: Retrieve full contact profiles, browse lists of contacts, and access detailed conversation metadata for analytics or personalized support.
- Widget and provider deployment: Quickly create and configure new widgets and providers to extend your AI’s reach across new channels and platforms.
- Datasource and metadata management: Fetch and inspect all data sources and custom contact fields, so your agent can sync, organize, or enrich customer data as needed.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `INSIGHTO_AI_ADD_INTENT_TO_ASSISTANT` | Add Intent To Assistant | Tool to add an intent to an assistant in Insighto.ai. Use when linking existing intents to an assistant for enhanced conversation handling. |
| `INSIGHTO_AI_CREATE_AGENCY` | Create Agency | Tool to create a new agency in Insighto.ai. Use when setting up a new agency with organization-specific configuration and branding. |
| `INSIGHTO_AI_CREATE_CONTACT_CUSTOM_FIELD` | Create Contact Custom Field | Tool to create a new contact custom field in Insighto.ai. Use when you need to add custom metadata fields for contacts. |
| `INSIGHTO_AI_CREATE_FORM` | Create Form | Tool to create a new form in Insighto.ai. Use when you need to create either a natural (conversational AI-driven) or simple (traditional) form for collecting information from users. |
| `INSIGHTO_AI_CREATE_INTENT` | Create Intent | Tool to create a new intent in Insighto.ai. Use when adding custom intents before training or deployment. Call after confirming intent attributes. |
| `INSIGHTO_AI_CREATE_PROMPT` | Create Prompt | Tool to create a new prompt in Insighto.ai. Use when adding custom prompts for AI interactions. The prompt template can include variables in {{variable_name}} format. |
| `INSIGHTO_AI_CREATE_PROVIDER` | Create Provider | Creates a new AI provider configuration (e.g., OpenAI, ElevenLabs, Azure Speech, Cartesia, PlayHT) for use in voice and text-to-speech workflows. The provider stores credentials and settings in the attributes field. |
| `INSIGHTO_AI_CREATE_TAG` | Create Tag | Tool to create a new tag in Insighto.ai. Use when categorizing contacts, conversations, or other entities with custom labels. |
| `INSIGHTO_AI_CREATE_TOOLFUNCTION` | Create Toolfunction | Tool to create a new toolfunction in Insighto.ai. Use when you need to register a new tool function (SDK, CURL, or query index type) before using it in workflows or assistant operations. |
| `INSIGHTO_AI_CREATE_WEBHOOK` | Create Webhook | Tool to create a new outbound webhook in Insighto.ai. Use when you need to configure webhook endpoints for event notifications. |
| `INSIGHTO_AI_CREATE_WIDGET` | Create Widget | Tool to create a new widget with specified attributes. Use after confirming assistant_id and widget_type. |
| `INSIGHTO_AI_DELETE_ASSISTANT_BY_ID` | Delete Assistant By ID | Tool to delete an assistant by its ID. Use when you need to permanently remove an assistant from the system. |
| `INSIGHTO_AI_DELETE_BULK_FORMS_BY_IDS` | Delete Bulk Forms By IDs | Tool to delete multiple forms by their IDs in a single operation. Use when you need to remove multiple forms at once. |
| `INSIGHTO_AI_DELETE_CONTACTS_IN_BULK` | Delete Contacts In Bulk | Tool to delete multiple contacts in bulk. Use when you need to remove several contacts at once by providing their UUIDs. |
| `INSIGHTO_AI_DELETE_FORM_BY_ID` | Delete Form By ID | Tool to delete a form by its unique identifier. Use when you need to permanently remove a form from the system. |
| `INSIGHTO_AI_DELETE_LINKED_ASSISTANT_DATASOURCE` | Delete Linked Assistant Datasource | Tool to delete (unlink) a datasource from a linked assistant in Insighto.ai. Use when you need to remove a specific datasource from an assistant's knowledge base. Requires valid datasource_id and assistant_id. |
| `INSIGHTO_AI_DELETE_LINK_TAG_ENTITY_BY_ID` | Delete Link Tag Entity By ID | Tool to delete a link_tag_entity by its ID. Use when you need to remove a specific link_tag_entity from the system. |
| `INSIGHTO_AI_DELETE_PROMPT_BY_ID` | Delete Prompt By ID | Tool to delete a prompt by its unique ID. Use when you need to remove a prompt from the system. |
| `INSIGHTO_AI_DELETE_PROVIDER_BY_ID` | Delete Provider By ID | Tool to delete an AI provider configuration by its unique identifier. Use when you need to permanently remove a provider from the system. |
| `INSIGHTO_AI_DELETE_TAG_BY_ID` | Delete Tag By ID | Tool to delete a tag by its unique identifier. Use when you need to permanently remove a tag from the system. |
| `INSIGHTO_AI_DELETE_TOOL_BY_ID` | Delete Tool By ID | Tool to delete a tool by its ID. Use when you need to remove a tool from the system. |
| `INSIGHTO_AI_DELETE_TOOLFUNCTION_BY_ID` | Delete Toolfunction By ID | Tool to delete a toolfunction by its ID. Use when you need to remove a toolfunction from the system. |
| `INSIGHTO_AI_DELETE_TWILIO_AUTH_BY_ID` | Delete Twilio Auth By ID | Tool to delete a Twilio authentication configuration by its ID. Use when you need to remove a Twilio auth integration from the system. |
| `INSIGHTO_AI_DELETE_USERWHATSAPP_BY_ID` | Delete UserWhatsApp By ID | Tool to delete a UserWhatsApp by its ID. Use when you need to remove a specific UserWhatsApp connection. |
| `INSIGHTO_AI_DELETE_WIDGET_BY_ID` | Delete Widget By ID | Tool to delete a widget by its unique ID. Use when you need to permanently remove a widget from the system. |
| `INSIGHTO_AI_GET_AGENCY_BILLING_PLAN` | Get Agency Billing Plan | Tool to retrieve details of a specific agency billing plan by ID. Use when you need to view billing plan information including limits for bots, queries, words, voice seconds, and support options. |
| `INSIGHTO_AI_GET_AGENCY_BRANDING_BY_ID` | Get Agency Branding By ID | Tool to retrieve branding configuration for a specific agency by agency ID. Use when you have a valid agency ID and need its branding settings. |
| `INSIGHTO_AI_GET_AGENT_LIST` | Get Agent List | Tool to fetch a paginated list of agents. Use when you need to retrieve user/agent information with pagination support. |
| `INSIGHTO_AI_GET_ASSISTANT_BY_ID` | Get Assistant By ID | Tool to retrieve details of a specific assistant by assistant ID. Use when you have a valid assistant ID and need the full assistant profile. |
| `INSIGHTO_AI_GET_CAPTURED_FORM_BY_FORM_ID` | Get Captured Form By Form ID | Tool to retrieve captured form submissions by form ID. Use when you have a valid form ID and need to fetch all submissions for that specific form with pagination support. |
| `INSIGHTO_AI_GET_CONTACT_BY_ID` | Get Contact By ID | Tool to retrieve details of a specific contact by contact ID. Use when you have a valid contact ID and need the full contact profile. |
| `INSIGHTO_AI_GET_DATASOURCE_BY_ID` | Get Datasource By ID | Tool to retrieve details of a specific datasource by datasource ID. Use when you have a valid datasource ID and need the full datasource details. |
| `INSIGHTO_AI_GET_INTENT_BY_ID` | Get Intent By ID | Tool to retrieve details of a specific intent by its ID. Use when you have a valid intent ID and need the full intent details. |
| `INSIGHTO_AI_GET_LIST_OF_CONTACTS` | Get List Of Contacts | Tool to fetch a paginated list of contacts. Use after confirming a valid API key to iterate through pages of contacts. |
| `INSIGHTO_AI_GET_LIST_OF_CONVERSATIONS` | Get List Of Conversations | Tool to fetch a list of conversations. Use after specifying date range and filters to retrieve conversation metadata. |
| `INSIGHTO_AI_GET_LIST_OF_DATASOURCES` | Get List Of Datasources | Retrieves a paginated list of data sources from Insighto AI. Data sources contain the knowledge base content (text, files, URLs) used by AI assistants. Use this to discover available data sources, get their IDs for further operations, or check if specific data sources exist. Requires admin or manager role. |
| `INSIGHTO_AI_GET_LIST_OF_DATA_SOURCES_LINKED_TO_ASSISTANT_ID` | Get List Of Data Sources Linked To Assistant Id | Tool to retrieve a paginated list of data sources linked to a specific assistant. Use when you need to discover which data sources are associated with an assistant ID. Requires admin or manager role. |
| `INSIGHTO_AI_GET_LIST_OF_WIDGETS_LINKED_TO_ASSISTANT_ID` | Get List Of Widgets Linked To Assistant Id | Tool to fetch a paginated list of widgets linked to a specific assistant. Use when you need to discover which widgets are associated with an assistant ID. |
| `INSIGHTO_AI_GET_PRICING_FOR_USER` | Get Pricing For User | Tool to retrieve pricing information for Insighto.ai services. Use when you need to calculate costs for LLM, voice, or transcription services. |
| `INSIGHTO_AI_GET_PROMPT_BY_ID` | Get Prompt By ID | Tool to retrieve details of a specific prompt by prompt ID. Use when you have a valid prompt ID and need the full prompt details. |
| `INSIGHTO_AI_GET_PROVIDER_BY_ID` | Get Provider By ID | Tool to retrieve details of a specific provider by provider ID. Use when you have a valid provider ID and need the full provider configuration. |
| `INSIGHTO_AI_GET_SPEECHTOTEXT_LIST` | Get Speechtotext List | Tool to fetch a paginated list of available speech-to-text voice configurations. Use when you need to retrieve available languages and providers for voice-to-text conversion. |
| `INSIGHTO_AI_GET_WIDGET_BY_ID` | Get Widget By ID | Tool to retrieve details of a specific widget by widget ID. Use when you have a valid widget ID and need the widget configuration. |
| `INSIGHTO_AI_LIST_CHANNELS` | List Channels | Tool to retrieve a paginated list of channels. Use after authenticating to fetch all available channels and their configurations. |
| `INSIGHTO_AI_READ_CAMPAIGN_CONTACT_LIST` | Read Campaign Contact List | Tool to retrieve a paginated list of contacts associated with a specific campaign. Use when you need to fetch all contacts enrolled in a campaign. |
| `INSIGHTO_AI_READ_CONTACT_CUSTOM_FIELD_LIST` | Read Contact Custom Field List | Tool to retrieve a list of custom fields associated with contacts. Use when you need to inspect or sync contact metadata definitions. |
| `INSIGHTO_AI_READ_CONTACT_SYNC_LOG_LIST` | Read Contact Sync Log List | Tool to retrieve a paginated list of contact sync logs. Use when you need to inspect sync history, troubleshoot sync issues, or audit contact synchronization operations. |
| `INSIGHTO_AI_READ_INTENTS_LIST` | Read Intents List | Tool to retrieve a list of all intents. Use after authenticating; supports pagination. |
| `INSIGHTO_AI_READ_TAG_LIST` | Read Tag List | Tool to retrieve a paginated list of tags. Use after authenticating to fetch and browse through all available tags. |
| `INSIGHTO_AI_READ_TOOL_FUNCTION_INVOKE_LOG_LIST` | Read Tool Function Invoke Log List | Tool to retrieve a paginated list of tool function invoke logs. Use when you need to inspect function invocation history, troubleshoot tool execution issues, or audit tool function calls. |
| `INSIGHTO_AI_READ_TOOL_TOOLFUNCTION_LIST` | Read Tool Toolfunction List | Tool to retrieve a paginated list of tool functions for a specific tool. Use after authenticating to fetch and browse through all tool functions associated with a given tool ID. |
| `INSIGHTO_AI_READ_TWILIO_AUTH_LIST` | Read Twilio Auth List | Tool to retrieve a paginated list of Twilio authentications. Use after authenticating to fetch and browse through all configured Twilio auth integrations. |
| `INSIGHTO_AI_RETRIEVE_LINKED_TOOL_AND_USER` | Retrieve Linked Tool And User | Tool to retrieve linked tool and user information for a specific tool. Use when you need to fetch users linked to a tool by tool ID. |
| `INSIGHTO_AI_RETRIEVE_LIST_OF_USER_CUSTOM_VOICE` | Retrieve List Of User Custom Voice | Tool to retrieve a paginated list of user custom voices. Use after authenticating to fetch available custom voices. |
| `INSIGHTO_AI_RETRIEVE_USER_MONTHLY_USAGES_AGGREGATION` | Retrieve User Monthly Usages Aggregation | Tool to retrieve user monthly usages aggregation data. Use when you need to fetch analytics about user usage patterns aggregated by month. |
| `INSIGHTO_AI_RETRIEVE_WEBHOOK_LOG` | Retrieve Webhook Log | Tool to retrieve webhook logs for a specific webhook. Use to monitor webhook delivery status and debug webhook issues. |
| `INSIGHTO_AI_SEND_MESSAGES_TO_CONTACTS` | Send Messages To Contacts | Tool to send messages to a list of contacts in bulk. Use when your widget is connected to WhatsApp or SMS and you have the contact IDs ready. |
| `INSIGHTO_AI_UPDATE_LINK_TOOL_USER` | Update Link Tool User | Tool to update a link tool user by its ID. Use when you need to modify properties of an existing tool integration. |
| `INSIGHTO_AI_UPDATE_TOOL_BY_ID` | Update Tool By ID | Tool to update a tool by its ID. Use when you need to modify properties of an existing tool such as name, description, or enabled status. |
| `INSIGHTO_AI_UPDATE_TOOLFUNCTION_BY_ID` | Update Toolfunction By ID | Tool to update an existing toolfunction by its ID. Use when you need to modify properties of a toolfunction such as name, description, type, or enabled status. |
| `INSIGHTO_AI_UPDATE_TWILIO_AUTH_BY_ID` | Update Twilio Auth By ID | Tool to update a Twilio authentication configuration by its ID. Use when you need to modify Twilio auth credentials or settings. |
| `INSIGHTO_AI_UPDATE_USER_PROFILE` | Update User Profile | Tool to update a user profile in Insighto.ai. Use when modifying user account details, contact information, or billing settings. |
| `INSIGHTO_AI_UPDATE_USERWHATSAPP_BY_ID` | Update UserWhatsApp By ID | Tool to update a UserWhatsApp configuration by its ID. Use when you need to modify WhatsApp Business API settings for a user. |
| `INSIGHTO_AI_UPDATE_WEBHOOK_BY_ID` | Update Webhook By ID | Tool to update an outbound webhook by its unique ID. Use when you need to modify webhook configuration such as name, endpoint URL, or enabled status. |
| `INSIGHTO_AI_UPSERT_CONTACT_BY_EMAIL_OR_PHONE_NUMBER` | Upsert Contact By Email Or Phone Number | Tool to upsert (create or update) a contact in Insighto.ai using email or phone number. Use when you need to create a new contact or update an existing one by email or phone number. |

## Supported Triggers

None listed.

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

The Insighto ai MCP server is an implementation of the Model Context Protocol that connects your AI agent to Insighto ai. It provides structured and secure access so your agent can perform Insighto ai 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 Insighto ai 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 Insighto ai-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: ["insighto_ai"],
  });

  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 Insighto ai 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 insighto_ai, 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 Insighto ai 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: ["insighto_ai"],
  });

  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 insighto_ai, 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 Insighto ai 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 Insighto ai MCP Agent with another framework

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

## Related Toolkits

- [Aeroleads](https://composio.dev/toolkits/aeroleads) - Aeroleads is a B2B lead generation platform for finding business emails and phone numbers. Grow your sales pipeline faster with powerful prospecting tools.
- [Autobound](https://composio.dev/toolkits/autobound) - Autobound is an AI-powered sales engagement platform that crafts hyper-personalized outreach and insights. It helps sales teams boost response rates and close more deals through tailored content and recommendations.
- [Better proposals](https://composio.dev/toolkits/better_proposals) - Better Proposals is a web-based tool for crafting and sending professional proposals. It helps teams impress clients and close deals faster with slick, easy-to-use templates.
- [Bidsketch](https://composio.dev/toolkits/bidsketch) - Bidsketch is a proposal software that helps businesses create professional proposals quickly and efficiently. It streamlines the proposal process, saving time while boosting client win rates.
- [Bolna](https://composio.dev/toolkits/bolna) - Bolna is an AI platform for building conversational voice agents. It helps businesses automate support and streamline interactions through natural, voice-powered conversations.
- [Botsonic](https://composio.dev/toolkits/botsonic) - Botsonic is a no-code AI chatbot builder for easily creating and deploying chatbots to your website. It empowers businesses to offer conversational experiences without writing code.
- [Botstar](https://composio.dev/toolkits/botstar) - BotStar is a comprehensive chatbot platform for designing, developing, and training chatbots visually on Messenger and websites. It helps businesses automate conversations and customer interactions without coding.
- [Callerapi](https://composio.dev/toolkits/callerapi) - CallerAPI is a white-label caller identification platform for branded caller ID and fraud prevention. It helps businesses boost customer trust while stopping spam, fraud, and robocalls.
- [Callingly](https://composio.dev/toolkits/callingly) - Callingly is a lead response management platform that automates immediate call and text follow-ups with new leads. It helps sales teams boost response speed and close more deals by connecting seamlessly with CRMs and lead sources.
- [Callpage](https://composio.dev/toolkits/callpage) - Callpage is a lead capture platform that lets businesses instantly connect with website visitors via callback. It boosts lead generation and increases your sales conversion rates.
- [Clearout](https://composio.dev/toolkits/clearout) - Clearout is an AI-powered service for verifying, finding, and enriching email addresses. It boosts deliverability and helps you discover high-quality leads effortlessly.
- [Clientary](https://composio.dev/toolkits/clientary) - Clientary is a platform for managing clients, invoices, projects, proposals, and more. It streamlines client work and saves you serious admin time.
- [Convolo ai](https://composio.dev/toolkits/convolo_ai) - Convolo ai is an AI-powered communications platform for sales teams. It accelerates lead response and improves conversion rates by automating calls and integrating workflows.
- [Delighted](https://composio.dev/toolkits/delighted) - Delighted is a customer feedback platform based on the Net Promoter System®. It helps you quickly gather, track, and act on customer sentiment.
- [Docsbot ai](https://composio.dev/toolkits/docsbot_ai) - Docsbot ai is a platform that lets you build custom AI chatbots trained on your documentation. It automates customer support and content generation, saving time and improving response quality.
- [Emelia](https://composio.dev/toolkits/emelia) - Emelia is an all-in-one B2B prospecting platform for cold-email, LinkedIn outreach, and prospect research. It streamlines outbound campaigns so you can find, engage, and warm up leads faster.
- [Findymail](https://composio.dev/toolkits/findymail) - Findymail is a B2B data provider offering verified email and phone contacts for sales prospecting. Enhance outreach with automated exports, email verification, and CRM enrichment.
- [Freshdesk](https://composio.dev/toolkits/freshdesk) - Freshdesk is customer support software with ticketing and automation tools. It helps teams streamline helpdesk operations for faster, better customer support.
- [Fullenrich](https://composio.dev/toolkits/fullenrich) - FullEnrich is a B2B contact enrichment platform that aggregates emails and phone numbers from 15+ data vendors. Instantly find and verify lead contact data to boost your outreach.
- [Gatherup](https://composio.dev/toolkits/gatherup) - GatherUp is a customer feedback and online review management platform. It helps businesses boost their reputation by streamlining how they collect and manage customer feedback.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Insighto ai MCP?

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

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

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

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