---
title: Use BSD from AI agents
description: Connect Claude, ChatGPT or any MCP-compatible agent to live sports data — and the endpoints agents can discover on their own.
---

# Use BSD from AI agents

BSD is built to be agent-friendly: native MCP servers, OAuth for one-click
connection, machine-readable discovery files, and every docs page available
as raw markdown.

## Connect via MCP (recommended)

Each sport runs a Model Context Protocol server speaking Streamable HTTP:

| Server URL | Sport | Access |
|---|---|---|
| `https://sports.bzzoiro.com/mcp` | Football — 26 tools | Free |
| `https://sports.bzzoiro.com/tennis/mcp` | Tennis | Sports Addon |
| `https://sports.bzzoiro.com/csgo/mcp` | CS2 | Sports Addon |
| `https://sports.bzzoiro.com/darts/mcp` | Darts | Sports Addon |
| `https://sports.bzzoiro.com/hockey/mcp` | Hockey | Sports Addon |
| `https://sports.bzzoiro.com/basketball/mcp` | Basketball | Sports Addon |
| `https://sports.bzzoiro.com/horseracing/mcp` | Horse racing | Sports Addon |

In Claude (web or desktop): **Settings → Connectors → Add custom connector**,
paste the server URL. The OAuth flow signs you in with your BSD account —
no manual token pasting. Clients that don't do OAuth can send
`Authorization: Token YOUR_API_KEY` instead.

Discovery probes (`initialize`, `tools/list`, `ping`) work unauthenticated,
so connector validation succeeds before you sign in; `tools/call` always
requires auth. Full tool reference: [MCP servers](/docs/mcp/).

## Docs for LLMs

Every page of this documentation is also plain markdown — append `.md`:

```
https://sports.bzzoiro.com/docs/football/events.md
https://sports.bzzoiro.com/docs/guides/league-page.md
```

Site-wide discovery files your agent can fetch:

| File | Contents |
|---|---|
| `/.well-known/llms.txt` | Index of the platform for LLMs |
| `/.well-known/llms-full.txt` | Expanded version |
| `/.well-known/pricing.md` | Machine-readable pricing |
| `/.well-known/mcp/server-card.json` | MCP server card |
| `/openapi.json` | Full OpenAPI 3 schema |

## Direct REST from agent code

Everything in these docs works from agent tool-code too — same token, same
endpoints. Two tips that matter for agents:

- Resolve ids through search endpoints, never guess them
  (`/api/v2/leagues/?country=…`, `/api/v2/players/?name=…`).
- Prefer the scoped OpenAPI schemas as tool definitions:
  `/static/docs/football-schema.json`, `tennis-schema.json`,
  `csgo-schema.json`, `darts-schema.json`, `hockey-schema.json`.

## Rate limits for automated clients

Same as everyone: 10 req/s per IP with generous burst — see
[Conventions & limits](/docs/conventions/). For live data loops, use the
[WebSockets](/docs/websocket/) instead of tight polling.