@racehooks/mcp
MCP server that gives AI assistants direct access to RaceHooks motorsport analytics and data, enabling management of webhooks, live sessions, simulations, and account usage.
README
@racehooks/mcp
MCP server for RaceHooks — gives AI assistants (Claude, Cursor, Windsurf) direct access to RaceHooks motorsport analytics and data.
RaceHooks is an independent service and is not affiliated with or endorsed by Formula One Management or the FIA. "Formula 1," "F1," and related marks are trademarks of Formula One Licensing BV.
What this does
Exposes your RaceHooks account as a set of tools and resources an AI assistant can call:
Tools (actions):
list_feeds/list_webhooks/get_webhook/create_webhook/delete_webhooktest_webhook/get_webhook_logsget_live_session/list_eventsget_subscription/get_usage/get_usage_by_feed/get_billing_planstart_simulation/list_simulations/get_simulation/cancel_simulation
Resources (read-only context):
racehooks://feeds— full feed catalogracehooks://live— current live session stateracehooks://webhooks— all webhook subscriptionsracehooks://usage— current delivery usage
Prompts (guided workflows):
setup_race_event_webhook— create anevents.racesubscription with filterssetup_fantasy_scoring_webhook— create a fantasy-optimised subscriptioncheck_account_health— full account health summary
Installation
npm install -g @racehooks/mcp
Or run directly with npx:
npx @racehooks/mcp
Get your API credentials at racehooks.io.
Configuration
Set two environment variables before starting:
export RACEHOOKS_CLIENT_ID="your-client-id"
export RACEHOOKS_CLIENT_SECRET="your-client-secret"
# Optional — defaults to https://api.racehooks.io
export RACEHOOKS_BASE_URL="https://api.racehooks.io"
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"racehooks": {
"command": "npx",
"args": ["-y", "@racehooks/mcp"],
"env": {
"RACEHOOKS_CLIENT_ID": "your-client-id",
"RACEHOOKS_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Claude Code (project config)
Add to .claude/settings.json in your project:
{
"mcpServers": {
"racehooks": {
"type": "stdio",
"command": "racehooks-mcp",
"env": {
"RACEHOOKS_CLIENT_ID": "your-client-id",
"RACEHOOKS_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Or with npx (no global install needed):
{
"mcpServers": {
"racehooks": {
"type": "stdio",
"command": "npx",
"args": ["-y", "@racehooks/mcp"],
"env": {
"RACEHOOKS_CLIENT_ID": "your-client-id",
"RACEHOOKS_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Cursor / Windsurf
Add to your MCP config (.cursor/mcp.json or equivalent):
{
"mcpServers": {
"racehooks": {
"command": "npx",
"args": ["-y", "@racehooks/mcp"],
"env": {
"RACEHOOKS_CLIENT_ID": "your-client-id",
"RACEHOOKS_CLIENT_SECRET": "your-client-secret"
}
}
}
}
Example usage with Claude
Once configured, you can ask Claude things like:
"Check my RaceHooks account health"
"Create an
events.racewebhook for https://myapp.com/hook, filtering for Ferrari only"
"Start a simulation of the 2025 Monaco GP qualifying against my webhooks at 10× speed"
"Show me which feeds are using the most delivery quota today"
"Set up a fantasy scoring webhook for my VER, NOR, LEC team at https://scoring.myapp.com/hook"
Security
The MCP server runs as a local stdio process — it never binds a network port. Your credentials are passed via environment variables, not included in tool calls or resource URIs.
All API calls are authenticated using OAuth 2 client credentials (token auto-refreshes before expiry).
Links
- RaceHooks console — sign up and manage your account
- RaceHooks API documentation
- Webhook API reference
- Feed catalog
- GitHub
- npm
- Smithery listing
- MCP specification
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。