How to integrate Api sports MCP with Vercel AI SDK v6

This guide walks you through connecting Api sports to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Api sports agent that can show today's football fixtures for la liga, get head-to-head record for chelsea vs arsenal, list injured players in premier league this week through natural language commands. This guide will help you understand how to give your Vercel AI SDK agent real control over a Api sports account through Composio's Api sports MCP server. Before we dive in, let's take a quick look at the key ideas and tools involved.

Get started for freeGet a demo
Api sports logoApi sports
Api Key

Api sports is a comprehensive sports data platform covering 2,000+ competitions with live scores and 15+ years of stats. Instantly access up-to-date sports information for analysis, apps, or chatbots.

67 Tools

Introduction

This guide walks you through connecting Api sports to Vercel AI SDK v6 using the Composio tool router. By the end, you'll have a working Api sports agent that can show today's football fixtures for la liga, get head-to-head record for chelsea vs arsenal, list injured players in premier league this week through natural language commands.

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

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

Also integrate Api sports with

ChatGPTOpenAI Agents SDKClaude Agent SDKClaude CodeClaude CoworkCodexOpenCodeCursorVS CodeOpenClawHermesCLIGoogle ADKLangChainMastra AILlamaIndexCrewAI

TL;DR

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

The Api sports MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Api sports account. It provides structured and secure access to rich sports data, so your agent can fetch fixtures, analyze team stats, retrieve player info, and explore historical match data on your behalf.

  • Live fixture and match retrieval: Instantly access upcoming and past football fixtures, filterable by league, team, date, or season for up-to-date match information.
  • Detailed match statistics and events: Have your agent pull granular match data, including goals, cards, substitutions, and in-depth statistics like possession, fouls, and passes for any fixture.
  • Team, coach, and player insights: Effortlessly fetch team rosters, coach histories, and individual player statistics or injury reports, making it easy to analyze team lineups and track player performance over time.
  • Head-to-head comparisons and historical data: Ask your agent to compare two teams’ direct matchups, review historical data, or examine league rounds, helping you make informed predictions or reports.
  • Dynamic country and league exploration: Let your agent discover available countries, leagues, and competitions, then drill down by code or search to tailor your sports data queries to specific needs.

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: ["api_sports"],
  });

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

  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 api_sports, 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 Api sports 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 Api sports action and event your agent gets out of the box.

Get AFL Games

Tool to retrieve AFL games and matches.

Get AFL Game Player Statistics

Tool to retrieve player statistics from AFL (Australian Football League) game(s).

Get AFL Seasons

Tool to get the list of available seasons for AFL.

Get AFL Standings

Tool to retrieve AFL standings for a league.

Get Baseball Games Head-to-Head

Tool to get head-to-head baseball games between two teams.

Get Basketball Bets

Tool to get all available basketball bet types.

Get Basketball Bookmakers

Tool to get all available basketball bookmakers.

Get basketball statistics

Tool to get basketball statistics for a team in a given league and season.

Get Formula 1 Circuits

Tool to get the list of available Formula 1 circuits.

Get Coaches

Tool to fetch coaches and their career history.

Get Countries

Tool to fetch available countries for league queries.

Get Fighters Records

Tool to get fighter career statistics.

Get Fixtures

Tool to retrieve football fixtures/matches.

Get fixtures events

Tool to get events (goals, cards, substitutions, VAR, etc.

Get Head-to-Head Fixtures

Tool to get head-to-head fixtures between two teams.

Get Fixture Lineups

Tool to retrieve starting XI and substitutes for a fixture.

Get fixtures players

Tool to get player statistics from a fixture.

Get Fixtures Rounds

Tool to get the rounds for a league or cup.

Get fixture statistics

Tool to get statistics for a fixture.

Get Formula 1 Competitions

Tool to retrieve Formula 1 competitions (Grand Prix races).

Get Formula 1 Races

Tool to retrieve Formula 1 race information for a given season.

Get Formula 1 Starting Grid

Tool to retrieve the starting grid for a Formula 1 race.

Get games events

Tool to get events (goals, penalties, etc.

Get AFL Games Quarters

Tool to retrieve AFL game quarter scores.

Get game statistics by teams

Tool to get team statistics from a game by ID.

Get Injuries

Tool to get injured or suspended players.

Get Leagues

Tool to retrieve leagues and cups.

Get League Seasons

Tool to get the list of available seasons for all leagues.

Get MMA Categories

Tool to fetch the list of all available MMA categories.

Get MMA Fighters

Tool to fetch MMA fighters data.

Get MMA Fights

Tool to retrieve the list of MMA fights according to given parameters.

Get MMA Fight Results

Tool to retrieve results from one or several MMA fights.

Get MMA Fighter Statistics

Tool to get fighter statistics from MMA fights.

Get NBA game statistics

Tool to get NBA game statistics including player stats for both teams.

Get NFL Standings Conferences

Tool to retrieve the list of available conferences for the NFL to be used in the standings endpoint.

Get Odds

Tool to fetch pre-match odds.

Get Odds Bets

Tool to get all available pre-match bet types.

Get Odds Bookmakers

Tool to list all available pre-match bookmakers.

Get In-Play Odds

Tool to fetch in-play odds for fixtures in progress.

Get Live Odds Bets

Tool to fetch all available bet types for in-play odds.

Get Odds Mapping

Tool to get the list of available fixture IDs for the odds endpoint.

Get Players

Tool to get player statistics.

Get Players Profiles

Tool to get the list of all available players.

Get Players Seasons

Tool to list all available seasons for player statistics.

Get Players Squads

Tool to get player squads.

Get player statistics

Tool to get player statistics for a specific basketball game.

Get Players Teams

Tool to get the list of teams and seasons in which a player played during his career.

Get Players Top Assists

Tool to get the 20 best players (top assists) for a league or cup.

Get Players Top Red Cards

Tool to get the 20 players with the most red cards for a league or cup.

Get Players Top Scorers

Tool to get the 20 best players (top scorers) for a league or cup.

Get Players Top Yellow Cards

Tool to get the 20 players with the most yellow cards for a league or cup.

Get Predictions

Tool to get predictions about a fixture.

Get Formula 1 Driver Rankings

Tool to retrieve Formula 1 driver rankings for a season.

Get Fastest Laps Rankings

Tool to get the ranking of the fastest laps for a Formula 1 race.

Get Race Rankings

Tool to retrieve rankings for a specific Formula 1 race.

Get Formula 1 Team Rankings

Tool to retrieve Formula 1 team rankings for a specific season.

Get Sidelined

Tool to get sidelined information (injuries, suspensions, etc.

Get Standings Divisions

Tool to retrieve the list of available divisions for an NFL competition to be used in the standings endpoint.

Get Standings Groups

Tool to retrieve the list of available groups for a league to be used in the standings endpoint.

Get Standings Stages

Tool to retrieve the list of available stages for a league to be used in the standings endpoint.

Get Teams

Tool to retrieve available teams.

Get Team Seasons

Tool to get the list of seasons available for a team.

Get team statistics

Tool to get detailed statistics of a team for a given league and season.

Get Timezone

Tool to fetch the complete list of available timezones for fixture queries.

Get Transfers

Tool to get all available transfers for players and teams.

Get Trophies

Tool to get trophies for a player or coach.

Get Venues

Tool to retrieve available venues.

FRAMEWORKS

How to build Api sports MCP Agent with another framework

ChatGPT logo

ChatGPT

Use Api sports MCP with ChatGPT

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Api sports MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Api sports MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Api sports MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Api sports MCP with Claude Cowork

Codex logo

Codex

Use Api sports MCP with Codex

Cursor logo

Cursor

Use Api sports MCP with Cursor

OpenClaw logo

OpenClaw

Use Api sports MCP with OpenClaw

Hermes logo

Hermes

Use Api sports MCP with Hermes

CLI logo

CLI

Use Api sports MCP with CLI

Google ADK logo

Google ADK

Use Api sports MCP with Google ADK

LangChain logo

LangChain

Use Api sports MCP with LangChain

Mastra AI logo

Mastra AI

Use Api sports MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Api sports MCP with LlamaIndex

CrewAI logo

CrewAI

Use Api sports MCP with CrewAI

OpenCode logo

OpenCode

Use Api sports MCP with OpenCode

VS Code logo

VS Code

Use Api sports MCP with VS Code

FAQ

Frequently asked questions

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

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

Start with Api sports.It takes 30 seconds.

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

Start building
Customer stories

Teams ship real agents on Composio

GET STARTED FOR FREEBOOK A DEMO
agent.aiZoomLettaGleanHubSpotAWSWabi

Karan skipped his own birthday party to fix our critical issue. It was 10pm and he diverted his Waymo to help us instead. This really sets the bar — it shows the commitment you need when users rely on your software.

Harsha Gaddipati
Harsha Gaddipati
Co-founder, Slashy

A lot of students tell us that the moment their connected tools start talking to each other inside Opennote feels almost magical. The agent just knows them, and it's immensely helped keep new users on the platform.

Abhi Arya
Abhi Arya
Co-founder, Opennote

We chose Composio over Pipedream because it delivered depth where it mattered — niche tools and tricky edge cases other platforms simply ignored. That gave us confidence to scale without compromising.

Nirman Dave
Nirman Dave
CEO, Zams

As a solo builder, shipping fast is life or death. The only way I can outcompete incumbents is by outmanoeuvring them. Getting bogged down managing agent auth would have been a death sentence.

Ryan Yu
Ryan Yu
Founder, Extra Thursday

Before Composio, adding tool integrations was slow and resource-intensive. Each one could take weeks of engineering time, and maintaining them meant constantly keeping up with API changes.

Tomisin Jenrola
Tomisin Jenrola
Founder & CEO, SwarmZero

With hands-on help from their founder, we integrated Gmail and Google Drive in just 30 minutes. This level of personal support and commitment is exactly what startups should strive for.

Jerome Leclanche
Jerome Leclanche
Co-Founder, Ingram Technologies