SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Composio search MCP with Vercel AI SDK v6

Connect Vercel AI SDK v6 to Composio search MCP. Find recent news about electric vehicles, search for top-rated hotels in paris, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Composio search logoComposio search
No Auth

Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.

21 Tools

Introduction

This guide walks you through connecting Composio search to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Composio search agent that can search the web and news, find flights and hotels, search shopping results, look up SEC filings, and fetch URL content through natural language commands.

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

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

Also integrate Composio search with

Claude CodeClaude CoworkOpenAI Agents SDKClaude Agent SDKGrok BotMuseCodexOpenClawHermesAtomic AgentGoogle ADKLangChainMastra AILlamaIndexCrewAIPydantic AIAutoGen

TL;DR

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

The Composio Search MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to Composio Search. It provides structured and secure access to web, travel, shopping, financial, news, and public filing search, so your agent can find flights and hotels, compare products, track markets, research current events, and retrieve public web content on your behalf.

  • Travel planning: Have your agent search flights, hotels, vacation rentals, and TripAdvisor recommendations for your next trip.
  • Product and deal discovery: Let the agent search Amazon and other shopping sources, compare prices, apply location preferences, and find deals.
  • Market and company research: Direct your agent to retrieve stock prices, market data, financial news, company information, and historical analysis.
  • News and web research: Instruct your agent to search current news and the wider web for relevant articles, sources, and information.
  • Filings and page retrieval: Have your agent find SEC filings such as annual, quarterly, and current reports, or extract readable text from public web pages.

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: ["composio_search"],
  });

  const mcpUrl = session.mcp.url;
What's happening:
  • We're creating a Tool Router session that gives your agent access to Composio search 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 Composio search-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 Composio search 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 composio_search, 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 Composio search 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 Composio search 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: ["composio_search"],
  });

  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 composio_search, 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 Composio search 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 Composio search action and event your agent gets out of the box.

Amazon Product Search

Search Amazon products across international marketplaces.

Composio DuckDuckGo Search

The DuckDuckGoSearch class utilizes the Composio DuckDuckGo Search API to perform searches, focusing on web information and details.

Composio Google Events Search

Search for upcoming events, concerts, festivals, conferences, and other activities.

Composio Similarlinks

Find links similar to a supplied URL using Exa, with optional domain, date, category and result-count filters.

Fetch URL Content

Fetch and extract clean, readable page text (markdown) from public web pages (HTML content) using the Exa API.

Composio Finance Search

Search Google Finance for stock quotes, indices, cryptocurrency prices, exchange rates, company financials and related news.

Flight Search

Search flights using a natural-language route or structured airport codes and dates.

Composio Google Maps Search

Search Google Maps for places by query, optionally using map coordinates and a pagination offset.

Groq Chat Completion

Generate chat completions using Groq models for tasks such as question answering, content generation, coding, summarization and translation.

Hotel Search

Search hotels and vacation rentals by location and stay dates, with price, class, cancellation and localization filters.

Composio Image Search

Search Google Images for image metadata and URLs, including original and thumbnail links.

Composio News Search

Search Google News results by query, time window, country and language.

NPPES NPI Registry Lookup

Lookup US healthcare provider details from the CMS NPI Registry (NPPES) using an NPI number or search filters.

Composio Scholar Search

Search Google Scholar for scholarly articles.

Composio SEC EDGAR Filings Search

Retrieve recent SEC EDGAR filing metadata for a company by ticker or CIK, optionally filtering by form type and constructing primary document and index URLs.

Composio Shopping Search

Search for products with advanced price filtering, location targeting, and deal discovery.

Composio LLM Search

Search a broad range of content using the Tavily API, with options for search depth, images, direct answers, domain filters, and the number of results.

Composio Trends Search

Search Google Trends for interest over time, regional comparisons, related topics, and related queries.

TripAdvisor Travel Search

Search TripAdvisor for attractions, restaurants, hotels, tours, and other travel information without a connected TripAdvisor account.

Walmart Product Search

Search Walmart products with optional minimum and maximum price filters.

Composio Web Search

Search the web using Exa's answer API, returning an AI-generated answer and source citations.

FRAMEWORKS

How to build Composio search MCP Agent with another framework

Claude Code logo

Claude Code

Use Composio search MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Composio search MCP with Claude Cowork

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Composio search MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Composio search MCP with Claude Agent SDK

Grok Bot logo

Grok Bot

Use Composio search MCP with Grok Bot

Muse logo

Muse

Use Composio search MCP with Muse

Codex logo

Codex

Use Composio search MCP with Codex

OpenClaw logo

OpenClaw

Use Composio search MCP with OpenClaw

Hermes logo

Hermes

Use Composio search MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Composio search MCP with Atomic Agent

Google ADK logo

Google ADK

Use Composio search MCP with Google ADK

LangChain logo

LangChain

Use Composio search MCP with LangChain

Mastra AI logo

Mastra AI

Use Composio search MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Composio search MCP with LlamaIndex

CrewAI logo

CrewAI

Use Composio search MCP with CrewAI

Pydantic AI logo

Pydantic AI

Use Composio search MCP with Pydantic AI

AutoGen logo

AutoGen

Use Composio search MCP with AutoGen

FAQ

Frequently asked questions

Start with Composio search.It takes 30 seconds.

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

Start building