SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Wit ai MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Wit ai MCP. Analyze user message for intent and entities, list all custom traits in your wit app, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Wit ai logoWit ai
Api Key

Wit.ai is a natural language processing platform that turns text or speech into structured data. It's perfect for building voice and chat interfaces that truly understand users.

31 Tools

Introduction

This guide walks you through connecting Wit ai to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Wit ai agent that can create and manage apps, define intents and entities, train with utterances, parse messages, and detect languages through natural language commands.

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

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

Also integrate Wit ai with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Wit 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 Wit ai account. It provides structured and secure access to your NLP resources, so your agent can create and manage apps, analyze natural language, organize intents and traits, and update configurations on your behalf.

  • Instant natural language analysis: Let your agent extract intents, entities, and traits from any text message using Wit.ai’s advanced NLP engine.
  • Automated app management: Easily create, update, or delete Wit.ai apps, enabling rapid deployment and maintenance of your language models.
  • Intent and trait organization: Have your agent list, retrieve details, or update all defined intents and traits, keeping your language understanding models organized and up to date.
  • Full app metadata access: Fetch comprehensive app settings and metadata for better monitoring, debugging, or auditing of your NLP solutions.
  • Seamless entity and trait customization: Programmatically add or configure traits for tailored entity recognition and improved intent matching.

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: ["wit_ai"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Wit 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 Wit ai-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 Wit ai 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 wit_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();
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 Wit 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

Complete Code

Here's the complete code to get you started with Wit ai 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: ["wit_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 wit_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 Wit 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.
TOOLS

Supported Tools

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

Add Entity Keyword

Tool to add a keyword with optional synonyms to a Wit.

Add Keyword Synonym

Tool to add a new synonym to a keyword in an entity.

Add Value to Trait

Tool to add a new value to an existing trait in Wit.

Create Wit.ai App

Tool to create a new app in Wit.

Create Wit.ai Entity

Tool to create a new entity in Wit.

Create Wit.ai Intent

Tool to create a new intent in Wit.

Create Wit.ai Trait

Create a new Wit.

Create Wit.ai Training Utterances

Tool to add training utterances (samples with annotations) to your Wit.

Delete App

Tool to delete a specific app from wit.

Delete Entity

Tool to permanently delete an entity by name.

Delete Entity Keyword

Tool to delete a keyword from a keywords entity in wit.

Delete Entity Role

Tool to delete a specific role from an entity in wit.

Delete Intent

Tool to permanently delete an intent by name.

Delete Keyword Synonym

Tool to delete a synonym from a keyword in an entity.

Delete Utterances

Tool to delete validated utterances (training samples) from your Wit.

Wit.ai Detect Language

Tool to detect the language of a given text input.

Export App Data

Tool to export Wit.

Get App Details

Retrieve metadata and settings for a Wit.

Get Entity Details

Tool to retrieve details of a specific entity including keywords and roles.

Get Intent Details

Tool to retrieve details of a specific intent.

Get Intents

List intents in a Wit.

Wit.ai Get Message

Tool to analyze a text message and extract its intent, entities, and traits.

Get Trait Details

Tool to retrieve details of a specific trait.

List Traits

Tool to list all traits in a Wit.

Get Voice Details

Tool to retrieve details for a specific text-to-speech voice.

List Wit.ai Apps

List Wit.

List App Tags

Tool to retrieve all tag groups (versions) for a Wit.

List Entities

Tool to list all entities in a Wit.

List Utterances

Tool to retrieve training utterances (samples) from a Wit.

List Voices

Tool to retrieve all available text-to-speech voices grouped by locale.

Update Wit.ai App

Tool to update an existing Wit.

FRAMEWORKS

How to build Wit ai MCP Agent with another framework

Claude Code logo

Claude Code

Use Wit ai MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Wit ai MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Wit ai MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Wit ai MCP with Claude Agent SDK

Codex logo

Codex

Use Wit ai MCP with Codex

OpenClaw logo

OpenClaw

Use Wit ai MCP with OpenClaw

Hermes logo

Hermes

Use Wit ai MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Wit ai MCP with Atomic Agent

Google ADK logo

Google ADK

Use Wit ai MCP with Google ADK

LangChain logo

LangChain

Use Wit ai MCP with LangChain

Mastra AI logo

Mastra AI

Use Wit ai MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Wit ai MCP with LlamaIndex

CrewAI logo

CrewAI

Use Wit ai MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Wit ai MCP with Pydantic AI

AutoGen logo

AutoGen

Use Wit ai MCP with AutoGen

FAQ

Frequently asked questions

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

Yes, absolutely. You can configure which Wit 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.

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 Wit ai data and credentials are handled as safely as possible.

Start with Wit ai.It takes 30 seconds.

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

Start building