Eventbrite MCP Server
A multi-tenant Model Context Protocol server that provides a secure interface to the Eventbrite API using Firebase authentication. It enables structured interaction with Eventbrite tools for event management while maintaining platform-managed credentials.
README
Eventbrite MCP Server
Multi-tenant Eventbrite MCP server with Firebase authentication, wrapping @prmichaelsen/eventbrite-mcp.
Overview
This server provides a multi-tenant Model Context Protocol (MCP) interface to the Eventbrite API. It uses:
- Firebase Authentication for user identity verification
- Platform API for secure credential management
- @prmichaelsen/mcp-auth for authentication wrapping
- @prmichaelsen/eventbrite-mcp as the base MCP server
Architecture
Client (Firebase JWT)
↓
Firebase Auth Provider (validates JWT → userId)
↓
Platform Token Resolver (userId → Eventbrite token via platform)
↓
Eventbrite MCP Server (executes tools)
↓
Eventbrite API
Prerequisites
- Node.js 20+
- Firebase project with authentication enabled
- Platform API that implements the credentials endpoint
- Eventbrite OAuth tokens stored in your platform
Installation
npm install
Configuration
Copy .env.example to .env and configure:
# Firebase (for JWT validation)
FIREBASE_PROJECT_ID=your-firebase-project-id
# Platform API (for token resolution)
PLATFORM_URL=https://your-platform.com
PLATFORM_SERVICE_TOKEN=your-service-token
# Server
PORT=8080
NODE_ENV=development
LOG_LEVEL=info
Environment Variables
| Variable | Required | Description |
|---|---|---|
FIREBASE_PROJECT_ID |
Yes | Firebase project ID for JWT validation |
PLATFORM_URL |
Yes | Base URL of your platform API |
PLATFORM_SERVICE_TOKEN |
Yes | Service token for platform API authentication |
PORT |
No | Server port (default: 8080) |
NODE_ENV |
No | Environment (development/production) |
LOG_LEVEL |
No | Logging level (default: info) |
Development
# Install dependencies
npm install
# Run in development mode with hot reload
npm run dev
# Build TypeScript
npm run build
# Run production build
npm start
Docker
Build
docker build -t eventbrite-mcp-server .
Run
docker run -p 8080:8080 \
-e FIREBASE_PROJECT_ID=your-project \
-e PLATFORM_URL=https://your-platform.com \
-e PLATFORM_SERVICE_TOKEN=your-token \
eventbrite-mcp-server
Deployment
Google Cloud Run
# Build and push to GCR
docker build -t gcr.io/YOUR_PROJECT/eventbrite-mcp-server:latest .
docker push gcr.io/YOUR_PROJECT/eventbrite-mcp-server:latest
# Generate service token
SERVICE_TOKEN=$(node -e "console.log(require('crypto').randomBytes(32).toString('base64url'))")
# Create secret
echo -n "$SERVICE_TOKEN" | gcloud secrets create platform-service-token --data-file=-
# Deploy
gcloud run deploy eventbrite-mcp-server \
--image gcr.io/YOUR_PROJECT/eventbrite-mcp-server:latest \
--region us-central1 \
--allow-unauthenticated \
--set-env-vars="FIREBASE_PROJECT_ID=your-project,PLATFORM_URL=https://your-platform.com,NODE_ENV=production" \
--update-secrets=PLATFORM_SERVICE_TOKEN=platform-service-token:latest \
--min-instances=0 \
--max-instances=10 \
--memory=512Mi \
--cpu=1
API Endpoints
Health Check
GET /mcp/health
MCP Message Endpoint
POST /mcp/message
Authorization: Bearer <firebase-jwt>
Content-Type: application/json
{
"jsonrpc": "2.0",
"method": "tools/list",
"id": 1
}
Testing
Local Testing
# Start server
npm start
# Test health endpoint
curl http://localhost:8080/mcp/health
# Test with Firebase JWT
curl -X POST http://localhost:8080/mcp/message \
-H "Authorization: Bearer <firebase-jwt>" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Production Testing
curl -X POST https://your-server.run.app/mcp/message \
-H "Authorization: Bearer <firebase-jwt>" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","method":"tools/list","id":1}'
Platform API Requirements
Your platform must implement the credentials endpoint:
// GET /api/credentials/eventbrite
// Headers:
// Authorization: Bearer <service-token>
// X-User-ID: <user-id>
// Response:
{
"access_token": "user-eventbrite-token",
"expires_at": "2024-12-31T23:59:59Z"
}
Project Structure
eventbrite-mcp-server/
├── src/
│ ├── index.ts # Main server entry point
│ └── auth/
│ ├── firebase-provider.ts # Firebase JWT validation
│ └── platform-token-resolver.ts # Platform API integration
├── agent/
│ └── patterns/
│ └── bootstrap.md # Bootstrap pattern documentation
├── package.json
├── tsconfig.json
├── Dockerfile
├── .env.example
├── .gitignore
├── .dockerignore
└── README.md
Features
- ✅ Multi-tenant architecture
- ✅ Firebase authentication
- ✅ Platform-managed credentials (secure)
- ✅ Stateless server (no database)
- ✅ Token caching for performance
- ✅ Rate limiting
- ✅ Health checks
- ✅ Docker support
- ✅ Cloud Run ready
Security
- Firebase JWT tokens are validated on every request
- Eventbrite tokens are never exposed to clients
- Service token authenticates server-to-platform communication
- All credentials are managed by the platform API
- Rate limiting prevents abuse
Caching
The server implements two levels of caching:
- Auth Cache: Firebase JWT validation results (TTL: 60s)
- Token Cache: Eventbrite access tokens (TTL: 5min)
Caching improves performance and reduces external API calls.
Troubleshooting
TypeScript Errors
TypeScript errors about missing modules are expected before running npm install. Install dependencies to resolve.
Authentication Failures
- Verify
FIREBASE_PROJECT_IDmatches your Firebase project - Ensure Firebase JWT is valid and not expired
- Check that the JWT is sent in the
Authorization: Bearer <token>header
Token Resolution Failures
- Verify
PLATFORM_URLis correct - Ensure
PLATFORM_SERVICE_TOKENis valid - Check that user has Eventbrite credentials in the platform
- Review platform API logs for errors
License
MIT
Related Projects
- @prmichaelsen/eventbrite-mcp - Base Eventbrite MCP server
- @prmichaelsen/mcp-auth - MCP authentication wrapper
- Bootstrap Pattern - Pattern documentation
Support
For issues or questions:
- Base MCP server: @prmichaelsen/eventbrite-mcp issues
- This wrapper: Create an issue in this repository
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。