How to Use the BallDontLie MCP in LlamaIndex

Index live NBA stats directly into your LlamaIndex vector stores for hallucination-free sports RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BallDontLie MCP to LlamaIndex

Create your Vinkius account to connect BallDontLie to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup BallDontLie with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Turn live NBA metrics into searchable knowledge

This MCP Server lets you build search indexes from real-time basketball data. Your agent pulls player profiles with `list_players` and immediately indexes those documents. Instead of guessing, your RAG applications query actual, live-updated stats. By feeding the output of `get_season_averages` into your vector index, you ground your agent's answers in hard numbers. It eliminates the hallucination problems common when asking models about specific athlete percentages.

Build queryable game history archives in LlamaIndex

You can feed historical match results directly into your local document store. Your agent uses `list_games` to gather historical matchups and `get_game_details` to pull the precise quarter-by-quarter breakdowns. This data becomes a structured knowledge base that your agent can query semantically. You can ask complex questions about team trends without writing custom SQL queries or parsing raw JSON manually.

Ground sports queries in verified data

When users ask about a player's recent performance, your agent pulls real-time facts instead of relying on its training data. It runs `list_player_stats` to get the latest box scores and merges them into the context window. The agent uses `get_team_details` to verify roster changes and division standings. This ensures every answer your application generates is backed by verified, structured NBA records.

Setup guide

Set up BallDontLie MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all BallDontLie MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to BallDontLie tools.",
)
response = await agent.run("List recent BallDontLie data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by BallDontLie. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect BallDontLie now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about BallDontLie MCP in LlamaIndex

Start by installing the LlamaIndex MCP tool spec via pip. Initialize the basic client with your Vinkius endpoint, then convert the server tools into a tool list. Pass that list to your FunctionAgent to start querying.

Yes, you can load the tool outputs directly into document objects. For example, you can fetch data using `get_season_averages` and store it in a vector index. This lets you run semantic searches over raw NBA statistics.

Yes, the tool spec supports asynchronous resolution for all NBA endpoints. Your agent can fetch player details and game stats concurrently, speeding up your RAG pipelines significantly.

You can use the allowed tools filter during initialization to restrict access. If you only want your agent to read team info, you can limit it to `list_teams` and `get_team_details`.

Your request payload is processed inside a zero-trust sandbox environment. This MCP setup ensures no search history or player query data is stored permanently on our servers, keeping your analytics workflow completely private.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript