# How to integrate Api sports MCP with LlamaIndex

```json
{
  "title": "How to integrate Api sports MCP with LlamaIndex",
  "toolkit": "Api sports",
  "toolkit_slug": "api_sports",
  "framework": "LlamaIndex",
  "framework_slug": "llama-index",
  "url": "https://composio.dev/toolkits/api_sports/framework/llama-index",
  "markdown_url": "https://composio.dev/toolkits/api_sports/framework/llama-index.md",
  "updated_at": "2026-05-12T10:01:30.751Z"
}
```

## Introduction

This guide walks you through connecting Api sports to LlamaIndex 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 LlamaIndex 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

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

## TL;DR

Here's what you'll learn:
- Set your OpenAI and Composio API keys
- Install LlamaIndex and Composio packages
- Create a Composio Tool Router session for Api sports
- Connect LlamaIndex to the Api sports MCP server
- Build a Api sports-powered agent using LlamaIndex
- Interact with Api sports through natural language

## What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.
Key features include:
- ReAct Agent: Reasoning and acting pattern for tool-using agents
- MCP Tools: Native support for Model Context Protocol
- Context Management: Maintain conversation context across interactions
- Async Support: Built for async/await patterns

## 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.

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `API_SPORTS_GET_AFL_GAMES` | Get AFL Games | Tool to retrieve AFL games and matches. Use when filtering games by id, date, league, season, team, or timezone to get upcoming, past, or live matches. |
| `API_SPORTS_GET_AFL_GAMES_STATISTICS_PLAYERS` | Get AFL Game Player Statistics | Tool to retrieve player statistics from AFL (Australian Football League) game(s). Use when you need detailed player performance data for specific AFL games by game ID, player ID, or season. |
| `API_SPORTS_GET_AFL_SEASONS` | Get AFL Seasons | Tool to get the list of available seasons for AFL. All seasons are 4-digit keys (e.g., 2018 for 2018-2019 season). Use when you need season filters for AFL endpoints. |
| `API_SPORTS_GET_AFL_STANDINGS` | Get AFL Standings | Tool to retrieve AFL standings for a league. Use when needing current team rankings, points, and positions for a specific season. |
| `API_SPORTS_GET_BASEBALL_GAMES_H2H` | Get Baseball Games Head-to-Head | Tool to get head-to-head baseball games between two teams. Use when comparing the match history between two specific baseball teams. |
| `API_SPORTS_GET_BASKETBALL_BETS` | Get Basketball Bets | Tool to get all available basketball bet types. Use when you need to retrieve available betting options for basketball games. |
| `API_SPORTS_GET_BASKETBALL_BOOKMAKERS` | Get Basketball Bookmakers | Tool to get all available basketball bookmakers. Use when you need to retrieve available bookmakers for basketball odds and betting data. |
| `API_SPORTS_GET_BASKETBALL_STATISTICS` | Get basketball statistics | Tool to get basketball statistics for a team in a given league and season. Use when you need detailed basketball team statistics including games played, wins, losses, points, and other performance metrics. |
| `API_SPORTS_GET_CIRCUITS` | Get Formula 1 Circuits | Tool to get the list of available Formula 1 circuits. Use when searching for circuits by id, competition, name, or search term. |
| `API_SPORTS_GET_COACHS` | Get Coaches | Tool to fetch coaches and their career history. Use when you need coach info by ID, team filter, or name search. |
| `API_SPORTS_GET_COUNTRIES` | Get Countries | Tool to fetch available countries for league queries. Use when filtering by name, code, or search string before retrieving leagues. |
| `API_SPORTS_GET_FIGHTERS_RECORDS` | Get Fighters Records | Tool to get fighter career statistics. Use when you need a fighter's complete record including wins, losses, draws, knockouts, and submissions. |
| `API_SPORTS_GET_FIXTURES` | Get Fixtures | Tool to retrieve football fixtures/matches. Use when filtering fixtures by id, date, league, season, team, or date ranges to get upcoming or past matches. Always provide at least one of season, date, team, or league to avoid oversized payloads. Never guess IDs — obtain valid league, season, team, or fixture IDs before calling this tool. |
| `API_SPORTS_GET_FIXTURES_EVENTS` | Get fixtures events | Tool to get events (goals, cards, substitutions, VAR, etc.) from a fixture. Use when you need detailed event data after confirming the fixture ID. |
| `API_SPORTS_GET_FIXTURES_HEADTOHEAD` | Get Head-to-Head Fixtures | Tool to get head-to-head fixtures between two teams. Use after determining team IDs to compare their direct match history. |
| `API_SPORTS_GET_FIXTURES_LINEUPS` | Get Fixture Lineups | Tool to retrieve starting XI and substitutes for a fixture. Use after confirming fixture ID; optionally filter by team, player, or section (startXI/substitutes). Lineups appear ~20-40 minutes before kickoff for supported competitions. |
| `API_SPORTS_GET_FIXTURES_PLAYERS` | Get fixtures players | Tool to get player statistics from a fixture. Use when you need detailed per-player stats for a specific match. Optionally filter by team. |
| `API_SPORTS_GET_FIXTURES_ROUNDS` | Get Fixtures Rounds | Tool to get the rounds for a league or cup. Use after confirming league and season to retrieve available round identifiers (optionally with dates) for filtering fixtures. |
| `API_SPORTS_GET_FIXTURES_STATISTICS` | Get fixture statistics | Tool to get statistics for a fixture. Use when you need detailed match stats (shots, fouls, possession, cards, passes, etc.), optionally filtered by team, statistic type, or including halftime data. |
| `API_SPORTS_GET_FORMULA1_COMPETITIONS` | Get Formula 1 Competitions | Tool to retrieve Formula 1 competitions (Grand Prix races). Use when filtering competitions by id, name, country, city, or search term. |
| `API_SPORTS_GET_FORMULA1_RACES` | Get Formula 1 Races | Tool to retrieve Formula 1 race information for a given season. Use when you need to get race schedules, results, or details for a specific Formula 1 competition season. |
| `API_SPORTS_GET_FORMULA1_RANKINGS_STARTINGGRID` | Get Formula 1 Starting Grid | Tool to retrieve the starting grid for a Formula 1 race. Use when you need to get the qualifying positions and times for drivers before a race starts. |
| `API_SPORTS_GET_GAMES_EVENTS` | Get games events | Tool to get events (goals, penalties, etc.) from a game. Use when you need detailed event data after confirming the game ID. |
| `API_SPORTS_GET_GAMES_QUARTERS` | Get AFL Games Quarters | Tool to retrieve AFL game quarter scores. Use when you need detailed scoring breakdown by quarter for one or multiple AFL games. |
| `API_SPORTS_GET_GAMES_STATISTICS_TEAMS` | Get game statistics by teams | Tool to get team statistics from a game by ID. Use when you need detailed team stats (assists, blocks, field goals, rebounds, steals, turnovers, etc.) for a specific game or multiple games. |
| `API_SPORTS_GET_INJURIES` | Get Injuries | Tool to get injured or suspended players. Use when you need a list of sidelined players filtered by league, season, fixture, team, player, date, ids, or timezone. |
| `API_SPORTS_GET_LEAGUES` | Get Leagues | Tool to retrieve leagues and cups. Use when filtering competitions by id, name, country, code, season, team, type, current, search, or last. |
| `API_SPORTS_GET_LEAGUES_SEASONS` | Get League Seasons | Tool to get the list of available seasons for all leagues. Use when you need season filters for other league endpoints. |
| `API_SPORTS_GET_MMA_CATEGORIES` | Get MMA Categories | Tool to fetch the list of all available MMA categories. Use when you need to get weight class categories (e.g., 'Flyweight', 'Lightweight', 'Heavyweight') for MMA fights. |
| `API_SPORTS_GET_MMA_FIGHTERS` | Get MMA Fighters | Tool to fetch MMA fighters data. Use when you need to get fighter information by id, team, name, category, or search term. |
| `API_SPORTS_GET_MMA_FIGHTS` | Get MMA Fights | Tool to retrieve the list of MMA fights according to given parameters. Use when filtering fights by id, date, season, fighter, or weight category to get upcoming or past MMA fight details. |
| `API_SPORTS_GET_MMA_FIGHTS_RESULTS` | Get MMA Fight Results | Tool to retrieve results from one or several MMA fights. Use when you need outcome details like victory method, round, time, knockout type, or judge scores for specific fights by id(s) or date. |
| `API_SPORTS_GET_MMA_FIGHTS_STATISTICS_FIGHTERS` | Get MMA Fighter Statistics | Tool to get fighter statistics from MMA fights. Use when you need detailed strike, takedown, and grappling statistics for fighters in specific fights or on a specific date. |
| `API_SPORTS_GET_NBA_GAMES_STATISTICS` | Get NBA game statistics | Tool to get NBA game statistics including player stats for both teams. Use when you need detailed statistics for a specific NBA game such as points, rebounds, assists, field goals, free throws, and other performance metrics. |
| `API_SPORTS_GET_NFL_STANDINGS_CONFERENCES` | Get NFL Standings Conferences | Tool to retrieve the list of available conferences for the NFL to be used in the standings endpoint. Use when you need to know which conferences are available for a specific NFL league and season before fetching detailed standings data. |
| `API_SPORTS_GET_ODDS` | Get Odds | Tool to fetch pre-match odds. Use when you need odds filterable by fixture, league, season, date, timezone, bookmaker, bet, or to navigate pages. |
| `API_SPORTS_GET_ODDS_BETS` | Get Odds Bets | Tool to get all available pre-match bet types. Use when filtering by bet ID or searching bet names before fetching odds. |
| `API_SPORTS_GET_ODDS_BOOKMAKERS` | Get Odds Bookmakers | Tool to list all available pre-match bookmakers. Use when you need to discover or filter bookmakers before fetching odds. |
| `API_SPORTS_GET_ODDS_LIVE` | Get In-Play Odds | Tool to fetch in-play odds for fixtures in progress. Use during live matches to get in-play odds. |
| `API_SPORTS_GET_ODDS_LIVE_BETS` | Get Live Odds Bets | Tool to fetch all available bet types for in-play odds. Use when you need to retrieve bet IDs or names (optionally filtering by id or search) before fetching live odds. |
| `API_SPORTS_GET_ODDS_MAPPING` | Get Odds Mapping | Tool to get the list of available fixture IDs for the odds endpoint. Use when you need to discover which fixtures have odds data available. |
| `API_SPORTS_GET_PLAYERS` | Get Players | Tool to get player statistics. Use when fetching players by id, team, league, season, search, or pagination. Returned player IDs are used as inputs to downstream tools such as fixtures statistics, predictions, and odds. |
| `API_SPORTS_GET_PLAYERS_PROFILES` | Get Players Profiles | Tool to get the list of all available players. Use when you need player profiles optionally filtered by ID, name search, or page. |
| `API_SPORTS_GET_PLAYERS_SEASONS` | Get Players Seasons | Tool to list all available seasons for player statistics. Use when building a player statistics query, optionally filtering by a specific player id. |
| `API_SPORTS_GET_PLAYERS_SQUADS` | Get Players Squads | Tool to get player squads. Use when fetching the current squad of a team (with team ID) or finding which teams a player belongs to (with player ID). |
| `API_SPORTS_GET_PLAYERS_STATISTICS` | Get player statistics | Tool to get player statistics for a specific basketball game. Use when you need detailed performance stats like points, rebounds, assists, field goals, three pointers, free throws, etc. Requires at least a game ID to retrieve player statistics. |
| `API_SPORTS_GET_PLAYERS_TEAMS` | Get Players Teams | Tool to get the list of teams and seasons in which a player played during his career. Use after confirming the player ID to retrieve club history. |
| `API_SPORTS_GET_PLAYERS_TOP_ASSISTS` | Get Players Top Assists | Tool to get the 20 best players (top assists) for a league or cup. Use after confirming league and season. |
| `API_SPORTS_GET_PLAYERS_TOP_RED_CARDS` | Get Players Top Red Cards | Tool to get the 20 players with the most red cards for a league or cup. Use after confirming league and season. |
| `API_SPORTS_GET_PLAYERS_TOP_SCORERS` | Get Players Top Scorers | Tool to get the 20 best players (top scorers) for a league or cup. Use after confirming league and season. |
| `API_SPORTS_GET_PLAYERS_TOP_YELLOW_CARDS` | Get Players Top Yellow Cards | Tool to get the 20 players with the most yellow cards for a league or cup. Use after confirming league and season. |
| `API_SPORTS_GET_PREDICTIONS` | Get Predictions | Tool to get predictions about a fixture. Use when you need calculated predictions for a given fixture ID. Predictions may not be available for all fixtures; empty or null responses indicate no predictions exist, not an error. |
| `API_SPORTS_GET_RANKINGS_DRIVERS` | Get Formula 1 Driver Rankings | Tool to retrieve Formula 1 driver rankings for a season. Use when querying driver standings, championship positions, or filtering by specific driver or team. |
| `API_SPORTS_GET_RANKINGS_FASTEST_LAPS` | Get Fastest Laps Rankings | Tool to get the ranking of the fastest laps for a Formula 1 race. Use when retrieving fastest lap times, speeds, and rankings by race, team, or driver. |
| `API_SPORTS_GET_RANKINGS_RACES` | Get Race Rankings | Tool to retrieve rankings for a specific Formula 1 race. Use when you need to get finishing positions, lap times, and pit stop information for drivers in a race. |
| `API_SPORTS_GET_RANKINGS_TEAMS` | Get Formula 1 Team Rankings | Tool to retrieve Formula 1 team rankings for a specific season. Use when you need to get championship standings showing teams ordered by points. |
| `API_SPORTS_GET_SIDELINED` | Get Sidelined | Tool to get sidelined information (injuries, suspensions, etc.). Use when you need current sidelined records filtered by player or coach. |
| `API_SPORTS_GET_STANDINGS_DIVISIONS` | Get Standings Divisions | Tool to retrieve the list of available divisions for an NFL competition to be used in the standings endpoint. Use when you need to know which divisions are available for a specific league and season before fetching detailed standings data. |
| `API_SPORTS_GET_STANDINGS_GROUPS` | Get Standings Groups | Tool to retrieve the list of available groups for a league to be used in the standings endpoint. Use when querying standings groups for a specific league and season before fetching detailed standings data. |
| `API_SPORTS_GET_STANDINGS_STAGES` | Get Standings Stages | Tool to retrieve the list of available stages for a league to be used in the standings endpoint. Use when you need to know which stages or groups are available for a specific league and season before fetching standings data. |
| `API_SPORTS_GET_TEAMS` | Get Teams | Tool to retrieve available teams. Use when filtering teams by id, name, league, season, country, code, venue, or search before fetching detailed team data. Team IDs are not inferrable from names; use `name` or `search` to look up and confirm the correct `id` before passing it to downstream requests. |
| `API_SPORTS_GET_TEAMS_SEASONS` | Get Team Seasons | Tool to get the list of seasons available for a team. Use when you need to know which seasons a specific team has data for. |
| `API_SPORTS_GET_TEAMS_STATISTICS` | Get team statistics | Tool to get detailed statistics of a team for a given league and season. Use after confirming league, season, and team ID. |
| `API_SPORTS_GET_TIMEZONE` | Get Timezone | Tool to fetch the complete list of available timezones for fixture queries. Use when you need valid timezone identifiers (e.g., 'Europe/London') before calling fixtures endpoints. |
| `API_SPORTS_GET_TRANSFERS` | Get Transfers | Tool to get all available transfers for players and teams. Use when you need transfer history filtered by player or team. |
| `API_SPORTS_GET_TROPHIES` | Get Trophies | Tool to get trophies for a player or coach. Use when you need to list honors filtered by player(s) or coach(es). |
| `API_SPORTS_GET_VENUES` | Get Venues | Tool to retrieve available venues. Use when filtering venues by id, name, city, country, or search before fetching detailed venue data. |

## Supported Triggers

None listed.

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

The Api sports MCP server is an implementation of the Model Context Protocol that connects your AI agent to Api sports. It provides structured and secure access so your agent can perform Api sports 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:
- Python 3.8/Node 16 or higher installed
- A Composio account with the API key
- An OpenAI API key
- A Api sports account and project
- Basic familiarity with async Python/Typescript

### 1. Getting API Keys for OpenAI, Composio, and Api sports

No description provided.

### 2. Installing dependencies

No description provided.
```python
pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv
```

```typescript
npm install @composio/llamaindex @llamaindex/openai @llamaindex/tools @llamaindex/workflow dotenv
```

### 3. Set environment variables

Create a .env file in your project root:
These credentials will be used to:
- Authenticate with OpenAI's GPT-5 model
- Connect to Composio's Tool Router
- Identify your Composio user session for Api sports access
```bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id
```

### 4. Import modules

No description provided.
```python
import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();
```

### 5. Load environment variables and initialize Composio

No description provided.
```python
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")
```

```typescript
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) throw new Error("OPENAI_API_KEY is not set");
if (!COMPOSIO_API_KEY) throw new Error("COMPOSIO_API_KEY is not set");
if (!COMPOSIO_USER_ID) throw new Error("COMPOSIO_USER_ID is not set");
```

### 6. Create a Tool Router session and build the agent function

What's happening here:
- We create a Composio client using your API key and configure it with the LlamaIndex provider
- We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, api sports)
- The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
- LlamaIndex will connect to this endpoint to dynamically discover and use the available Api sports tools.
- The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.
```python
async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["api_sports"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Api sports actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Api sports actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)
```

```typescript
async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["api_sports"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
        description : "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Api sports actions." ,
    llm,
    tools,
  });

  return agent;
}
```

### 7. Create an interactive chat loop

No description provided.
```python
async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")
```

```typescript
async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}
```

### 8. Define the main entry point

What's happening here:
- We're orchestrating the entire application flow
- The agent gets built with proper error handling
- Then we kick off the interactive chat loop so you can start talking to Api sports
```python
async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err) {
    console.error("Failed to start agent:", err);
    process.exit(1);
  }
}

main();
```

### 9. Run the agent

When prompted, authenticate and authorise your agent with Api sports, then start asking questions.
```bash
python llamaindex_agent.py
```

```typescript
npx ts-node llamaindex-agent.ts
```

## Complete Code

```python
import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["api_sports"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Api sports actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Api sports actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")
```

```typescript
import "dotenv/config";
import readline from "node:readline/promises";
import { stdin as input, stdout as output } from "node:process";

import { Composio } from "@composio/core";
import { LlamaindexProvider } from "@composio/llamaindex";

import { mcp } from "@llamaindex/tools";
import { agent as createAgent } from "@llamaindex/workflow";
import { openai } from "@llamaindex/openai";

dotenv.config();

const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const COMPOSIO_API_KEY = process.env.COMPOSIO_API_KEY;
const COMPOSIO_USER_ID = process.env.COMPOSIO_USER_ID;

if (!OPENAI_API_KEY) {
    throw new Error("OPENAI_API_KEY is not set in the environment");
  }
if (!COMPOSIO_API_KEY) {
    throw new Error("COMPOSIO_API_KEY is not set in the environment");
  }
if (!COMPOSIO_USER_ID) {
    throw new Error("COMPOSIO_USER_ID is not set in the environment");
  }

async function buildAgent() {

  console.log(`Initializing Composio client...${COMPOSIO_USER_ID!}...`);
  console.log(`COMPOSIO_USER_ID: ${COMPOSIO_USER_ID!}...`);

  const composio = new Composio({
    apiKey: COMPOSIO_API_KEY,
    provider: new LlamaindexProvider(),
  });

  const session = await composio.create(
    COMPOSIO_USER_ID!,
    {
      toolkits: ["api_sports"],
    },
  );

  const mcpUrl = session.mcp.url;
  console.log(`Composio Tool Router MCP URL: ${mcpUrl}`);

  const server = mcp({
    url: mcpUrl,
    clientName: "composio_tool_router_with_llamaindex",
    requestInit: {
      headers: {
        "x-api-key": COMPOSIO_API_KEY!,
      },
    },
    // verbose: true,
  });

  const tools = await server.tools();

  const llm = openai({ apiKey: OPENAI_API_KEY, model: "gpt-5" });

  const agent = createAgent({
    name: "composio_tool_router_with_llamaindex",
    description:
      "An agent that uses Composio Tool Router MCP tools to perform actions.",
    systemPrompt:
      "You are a helpful assistant connected to Composio Tool Router."+
"Use the available tools to answer user queries and perform Api sports actions." ,
    llm,
    tools,
  });

  return agent;
}

async function chatLoop(agent: ReturnType<typeof createAgent>) {
  const rl = readline.createInterface({ input, output });

  console.log("Type 'quit' or 'exit' to stop.");

  while (true) {
    let userInput: string;

    try {
      userInput = (await rl.question("\nYou: ")).trim();
    } catch {
      console.log("\nAgent: Bye!");
      break;
    }

    if (!userInput) {
      continue;
    }

    const lower = userInput.toLowerCase();
    if (lower === "quit" || lower === "exit") {
      console.log("Agent: Bye!");
      break;
    }

    try {
      process.stdout.write("Agent: ");

      const stream = agent.runStream(userInput);
      let finalResult: any = null;

      for await (const event of stream) {
        // The event.data contains the streamed content
        const data: any = event.data;

        // Check for streaming delta content
        if (data?.delta) {
          process.stdout.write(data.delta);
        }

        // Store final result for fallback
        if (data?.result || data?.message) {
          finalResult = data;
        }
      }

      // If no streaming happened, show the final result
      if (finalResult) {
        const answer =
          finalResult.result ??
          finalResult.message?.content ??
          finalResult.message ??
          "";
        if (answer && typeof answer === "string" && !answer.includes("[object")) {
          process.stdout.write(answer);
        }
      }

      console.log(); // New line after streaming completes
    } catch (err: any) {
      console.error("\nAgent error:", err?.message ?? err);
    }
  }

  rl.close();
}

async function main() {
  try {
    const agent = await buildAgent();
    await chatLoop(agent);
  } catch (err: any) {
    console.error("Failed to start agent:", err?.message ?? err);
    process.exit(1);
  }
}

main();
```

## Conclusion

You've successfully connected Api sports to LlamaIndex through Composio's Tool Router MCP layer.
Key takeaways:
- Tool Router dynamically exposes Api sports tools through an MCP endpoint
- LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
- The agent becomes more capable without increasing prompt size
- Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

## How to build Api sports MCP Agent with another framework

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

## Related Toolkits

- [Excel](https://composio.dev/toolkits/excel) - Microsoft Excel is a robust spreadsheet application for organizing, analyzing, and visualizing data. It's the go-to tool for calculations, reporting, and flexible data management.
- [21risk](https://composio.dev/toolkits/_21risk) - 21RISK is a web app built for easy checklist, audit, and compliance management. It streamlines risk processes so teams can focus on what matters.
- [Abstract](https://composio.dev/toolkits/abstract) - Abstract provides a suite of APIs for automating data validation and enrichment tasks. It helps developers streamline workflows and ensure data quality with minimal effort.
- [Addressfinder](https://composio.dev/toolkits/addressfinder) - Addressfinder is a data quality platform for verifying addresses, emails, and phone numbers. It helps you ensure accurate customer and contact data every time.
- [Agentql](https://composio.dev/toolkits/agentql) - Agentql is a toolkit that connects AI agents to the web using a specialized query language. It enables structured web interaction and data extraction for smarter automations.
- [Agenty](https://composio.dev/toolkits/agenty) - Agenty is a web scraping and automation platform for extracting data and automating browser tasks—no coding needed. It streamlines data collection, monitoring, and repetitive online actions.
- [Ambee](https://composio.dev/toolkits/ambee) - Ambee is an environmental data platform providing real-time, hyperlocal APIs for air quality, weather, and pollen. Get precise environmental insights to power smarter decisions in your apps and workflows.
- [Ambient weather](https://composio.dev/toolkits/ambient_weather) - Ambient Weather is a platform for personal weather stations with a robust API for accessing local, real-time, and historical weather data. Get detailed environmental insights directly from your own sensors for smarter apps and automations.
- [Anonyflow](https://composio.dev/toolkits/anonyflow) - Anonyflow is a service for encryption-based data anonymization and secure data sharing. It helps organizations meet GDPR, CCPA, and HIPAA data privacy compliance requirements.
- [Api ninjas](https://composio.dev/toolkits/api_ninjas) - Api ninjas offers 120+ public APIs spanning categories like weather, finance, sports, and more. Developers use it to supercharge apps with real-time data and actionable endpoints.
- [Apify](https://composio.dev/toolkits/apify) - Apify is a cloud platform for building, deploying, and managing web scraping and automation tools called Actors. It lets you automate data extraction and workflow tasks at scale—no infrastructure headaches.
- [Autom](https://composio.dev/toolkits/autom) - Autom is a lightning-fast search engine results data platform for Google, Bing, and Brave. Developers use it to access fresh, low-latency SERP data on demand.
- [Beaconchain](https://composio.dev/toolkits/beaconchain) - Beaconchain is a real-time analytics platform for Ethereum 2.0's Beacon Chain. It provides detailed insights into validators, blocks, and overall network performance.
- [Big data cloud](https://composio.dev/toolkits/big_data_cloud) - BigDataCloud provides APIs for geolocation, reverse geocoding, and address validation. Instantly access reliable location intelligence to enhance your applications and workflows.
- [Bigpicture io](https://composio.dev/toolkits/bigpicture_io) - BigPicture.io offers APIs for accessing detailed company and profile data. Instantly enrich your applications with up-to-date insights on 20M+ businesses.
- [Bitquery](https://composio.dev/toolkits/bitquery) - Bitquery is a blockchain data platform offering indexed, real-time, and historical data from 40+ blockchains via GraphQL APIs. Get unified, reliable access to complex on-chain data for analytics, trading, and research.
- [Brightdata](https://composio.dev/toolkits/brightdata) - Brightdata is a leading web data platform offering advanced scraping, SERP APIs, and anti-bot tools. It lets you collect public web data at scale, bypassing blocks and friction.
- [Builtwith](https://composio.dev/toolkits/builtwith) - BuiltWith is a web technology profiler that uncovers the technologies powering any website. Gain actionable insights into analytics, hosting, and content management stacks for smarter research and lead generation.
- [Byteforms](https://composio.dev/toolkits/byteforms) - Byteforms is an all-in-one platform for creating forms, managing submissions, and integrating data. It streamlines workflows by centralizing form data collection and automation.
- [Cabinpanda](https://composio.dev/toolkits/cabinpanda) - Cabinpanda is a data collection platform for building and managing online forms. It helps streamline how you gather, organize, and analyze responses.

## Frequently Asked Questions

### What are the differences in Tool Router MCP and Api sports MCP?

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.

### Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex 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.

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

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.

### 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 Api sports data and credentials are handled as safely as possible.

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