BallDontLie MCP for AI. Analyze any NBA game or player stat.
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
BallDontLie provides instant access to deep NBA data through one MCP. Pull player profiles, team technical details, and historical game results directly into your AI agent.
It lets you audit rosters, calculate season averages, and track scores without manually checking sports websites.
What your AI can do
Get game details
Pulls all the specific outcomes and stats for a single, given NBA game.
Get player details
Retrieves comprehensive technical data about any individual NBA player.
Get team details
Gets the full technical profile and roster information for any NBA team.
Search for specific NBA players and pull their full metadata details.
Get technical identifying information for every team in the league.
Retrieve lists of games, including scores and outcomes, filtered by date or season.
Determine a player's average points, rebounds, and assists over an entire season.
Pull the detailed results and statistics for one particular matchup.
Ask an AI about this
Waiting for input…
BallDontLie: 8 Basketball Data Tools
Use these tools to retrieve everything from single player profiles to league-wide team rosters. Your agent handles all the data calls.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using BallDontLie on VinkiusGet Game Details
Pulls all the specific outcomes and stats for a single, given NBA game.
Get Player Details
Retrieves comprehensive technical data about any individual NBA player.
Get Team Details
Gets the full technical profile and roster information for any NBA team.
List Games
Generates a list of past or upcoming NBA games, including basic scores and dates.
List Players
Searches and lists thousands of NBA players by name, status, or ID.
List Player Stats
Fetches a detailed breakdown of player statistics for one or more specific game matchups.
List Teams
Lists the official names and technical identifiers for all thirty NBA teams.
Get Season Averages
Calculates a specific player's performance averages over an entire basketball season.
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with BallDontLie, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,100+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 8 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Tracking NBA data usually means jumping between multiple sports sites.
Today, if you want to know how a player performed in a key matchup, you often start at one site just for the scores. Then you have to jump to another site to check their career stats, and maybe a third site for team roster depth. You spend ten minutes copy-pasting numbers into a spreadsheet that isn't even complete.
With this MCP connected through Vinkius, your agent pulls everything together in one chat exchange. Instead of multiple tabs and manual lookups, you ask it to find the player stats and game scores for a specific date range, and boom—you get clean, structured data ready for use.
BallDontLie MCP delivers precise insights using `get_season_averages`.
Before this, finding a player's season average was a multi-step process. You had to find the general statistics page, filter by year, and hope they displayed the exact metric you needed—and if not, you were stuck.
Now, just tell your agent which player ID and what year you want. The `get_season_averages` tool pulls that single number directly. It’s that simple.
What your AI can actually do with this
This connector gives your AI agent direct access to comprehensive basketball data. You can search for thousands of active or retired players, pull specific team technical details, or retrieve the results from past games. Instead of navigating multiple sports sites, your agent acts like a dedicated analyst, pulling together everything you need through natural conversation.
If you're running complex analytics, Vinkius makes sure this MCP is easily discoverable alongside thousands of others.
Need to track season averages? You can do that. Want to check the roster for all 30 teams? Your agent handles it. It’s about getting reliable basketball intelligence instantly.
019d841b-934b-70d1-a006-29c50d9316b7 Here's how it actually works
The bottom line is that you tell the MCP what kind of basketball data you need, and it pulls back the exact metrics without you ever leaving your client environment.
Start by listing or searching for a player, team, or date range to narrow down your data scope.
The MCP then gathers the necessary unique identifiers (like an ID) and executes the appropriate retrieval function.
Your AI agent returns clean, structured data—whether it’s a list of players or specific season averages—ready for use in your application.
Who is this actually for?
Sports analysts who hate copy-pasting stats from websites. Fantasy players tired of manual roster checks at 2 a.m. Data scientists needing clean, structured NBA data for models. Anyone whose job involves tracking performance trends in professional sports.
Uses the MCP to check specific player statistics and calculate season averages before setting their weekly lineup.
Runs comparative analysis, pulling together multiple game results or detailed team metrics for a client presentation.
Retrieves historical game data and player metadata to write articles or commentary about past seasons.
What Changes When You Connect
Stop manually checking stats websites. Instead of jumping between pages, your agent pulls all needed data—whether it's running a query with list_players or pulling scores using list_games—and gives you one clean answer.
Deep dive into player performance history. Use get_season_averages to calculate multi-year trends for any athlete, helping you spot subtle changes in their game that simple stats miss.
Audit team rosters instantly. If you need the full technical details for all 30 teams, use list_teams and then check specific squad info with get_team_details. It’s fast.
Get the granular picture of a single match. When you run get_game_details, you don't just get the final score; you get the underlying statistics for every player involved in that game.
Building complex workflows is easy. You can use list_games to find date ranges, then pass those IDs into other tools like list_player_stats to build a full report automatically.
See it in action
A journalist needs last year's key matchup stats.
Instead of finding old box scores and manually compiling numbers, the agent runs list_games for the desired season. It then uses get_game_details on specific dates to pull all necessary player statistics and team totals in one go.
A fantasy player needs to compare two rivals.
The agent runs list_players for both athletes. Then, it uses get_season_averages on each profile ID to get a clean comparison of their points and rebounds from the last three seasons.
A data scientist wants all player identifiers.
The agent first calls list_teams for all available team IDs. Then, it runs get_team_details on each ID to build a complete dataset of every unique identifier needed for subsequent statistical modeling.
Checking the scores from a specific date.
The agent uses list_games, filtering by yesterday's date. It then asks the client to pull get_game_details for the top 3 games listed, giving immediate results without needing multiple API calls.
The honest tradeoffs
Asking for 'all stats'
Prompting the agent: 'Give me everything about LeBron James.' This vague request will likely fail or return a massive, unusable data dump.
Be specific. First, use list_players to confirm his ID. Then, ask for get_season_averages using that precise ID and the desired season year.
Listing tools sequentially
A developer calls list_teams, then immediately follows up by calling get_team_details on every single team ID listed. This is inefficient over-fetching.
Only use get_team_details when you need the full roster or technical details for a known, specific team. Use list_teams just to verify names.
Confusing game lists with stats
Trying to get player performance data simply by running list_games. This only provides scores and basic results, not individual player metrics.
Use list_games first to find the matchup ID. Once you have that ID, use get_game_details or list_player_stats for the actual numbers.
When It Fits, When It Doesn't
You should use this MCP if your project requires deep, structured access to historical professional basketball data—think statistics, season trends, and team composition. You need it when you can't rely on scraping a website because the data structure changes too often.
Don't use this if all you need is basic news or general league standings; those are usually available via simpler, dedicated sports feeds. Also, don't try to analyze coach performance metrics—the current tool set only covers player and team roster stats. Stick to list_players, get_season_averages, and the game-related tools for reliable results.
Questions you might have
How do I use the get_player_details tool with BallDontLie? +
You provide the specific player ID and ask for details. The agent will return metadata like their current team, height, and basic bio information.
Can list_games show me scores from last week using BallDontLie? +
Yes. You prompt the MCP to use list_games and specify a date range. It returns a list of games played, including basic outcomes for those dates.
What is required for get_game_details using BallDontLie? +
You must provide the unique ID for a game matchup. This ID usually comes from running list_games first so you know which specific game to detail.
Does list_players include retired athletes? (BallDontLie) +
Yes, list_players can search across both active and retired NBA players. Just specify the player's name or ID in your prompt.
How do I handle authentication when using tools like get_player_details? +
You must provide your dedicated BallDontLie API Key within your MCP client settings. Once connected, your agent uses this key to authenticate every request, ensuring secure access to the data.
What specific metrics does the get_season_averages tool return? +
The tool returns calculated averages for core performance indicators like points, rebounds, and assists. These figures represent a player's average contribution per game over the specified season.
Are there usage limits when I call list_player_stats frequently? +
Yes, the platform manages API usage quotas to ensure stable performance for all users. Refer to the Vinkius documentation for current rate limit details and bulk request guidelines.
How do I find unique identifiers after running list_teams? +
The tool lists every NBA team, providing both their technical names and unique IDs. You must capture these specific identifiers to target accurate data retrieval in subsequent calls.
Can I search for a specific player by name? +
Yes! Use the list_players tool and provide the name in the search parameter. Your agent will return a list of matching players with their unique IDs and metadata.
How do I see the scores for all games played on a specific date? +
Use the list_games tool and provide the date in the dates parameter (format YYYY-MM-DD). The response will include all games played on that day with their final scores.
Does the integration provide player season averages? +
Absolutely. Use the get_season_averages tool by providing the specific season year and the player IDs. This will return averaged performance metrics for the requested period.
We've already built the connector for BallDontLie. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 8 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.