OpenTicket MCP Server
Enables agents to discover events, purchase tickets, and set reminders through MCP tools.
README
OpenTicket
Your agent handles the checkout.
OpenTicket is an agent-native ticketing platform: every ticket is discoverable and purchasable by an AI agent — not just by a human clicking "buy". An agent finds the event, pays within the user's spending limit via Stripe, gets the ticket issued, and the buyer receives an email with a calendar invite (.ics) with reminders. No scraping, no browser automation, no human in the loop.
$ your-agent: "get me a ticket for the jazz night on Friday, up to $50"
✓ search_events("jazz") → evt_a1b2 · Jazz Night · $35
✓ buy_ticket(spend_limit: $50) → pending_payment · checkout_url
✓ payment confirmed → ticket tkt_9f8e · .ics sent to your inbox
Buy tickets with your agent
The fastest path — install the OpenTicket skills once and your agent knows how to discover and buy on its own:
npx skills add LucasLeguizamo/openticket-skills --copy
Then just say: "find me a ticket for the jazz night on Friday and buy it — up to $50."
Or connect via MCP directly
Point any MCP client (Claude, or your own agent) at the server:
{
"mcpServers": {
"openticket": { "url": "https://<host>/api/mcp" }
}
}
| Tool | What it does |
|---|---|
search_events |
Find published events with ticket types, prices, and remaining availability |
get_ticket |
Inspect a ticket type before buying |
buy_ticket |
Purchase within a spend_limit; returns pending_payment + a Stripe checkout_url |
get_order |
Poll order status; returns tickets and the .ics link once confirmed |
set_reminder |
Schedule an email reminder with a .ics (24h and 1h alarms) |
Rules of the road for agents:
- Idempotency: you generate the
idempotency_keyand reuse it on every retry — retries return the same order, never a double charge. - Spending limits:
buy_ticketrequires aspend_limit(amount + currency). Purchases above it are rejected withmandate_exceededbefore any charge. - Structured errors:
sold_out,mandate_exceeded,invalid_intent,event_unavailable,payment_failed— machine-readable, safe to branch on. - Discovery tools are open;
buy_ticketrequires an API key (Authorization: Bearer).
Discovery without MCP
| Endpoint | Purpose |
|---|---|
GET /api/events |
Public JSON feed: published events, ticket types, prices (minor units), live availability |
GET /llms.txt |
Plain-text instructions for agents that don't speak MCP (llmstxt.org) |
GET /openapi.json |
OpenAPI 3.1 spec of the public endpoints |
GET /api/ticker |
Live activity stream (SSE), PII-free |
For organizers
Create an event with ticket types, prices, and quotas; publish it; done — your tickets are instantly purchasable by every agent that speaks MCP, with zero integration work on your side. Flat 5% platform fee, same for human and agent sales. Inventory is enforced atomically in the database: no overselling, even with dozens of agents racing for the last ticket.
How it works
agent ──MCP──▶ ┌─────────────────────────────────────────────┐
web ──UI───▶ │ PurchaseCore (framework-free, core/) │
│ idempotency → spend limit → atomic reserve │──▶ Stripe hosted checkout
│ → order → [webhook] → issue → email + .ics │
└─────────────────────────────────────────────┘
One purchase pipeline, thin adapters per rail. Live today: MCP and web. On the roadmap behind the same adapter: ACP (OpenAI/Stripe Agentic Commerce Protocol), x402 (HTTP 402 / stablecoin), AP2 (mandates as verifiable credentials).
Development & self-hosting
Contributor setup, test harness, and architecture notes: docs/DEVELOPMENT.md. Product spec lives in PRD.md and docs/.
License
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。