mcpie
An MCP server that lets you order your usual pizza from Domino's with a single tool call, using cash at pickup. It supports checking store status, menus, coupons, and dry-run pricing, with a hard confirmation gate before placing real orders.
README
mcpie 🍕
The standing-order pizza button. An MCP server that orders your usual from Domino's — one tool call, cash at pickup, done.
Most pizza MCP servers hand your AI a shopping cart. mcpie hands it a button. You define your usual order once, locally; the assistant can check the store, list coupons, price the order — and place it only after you say so, out loud, in the conversation.
You: order the pizza
Claude: [pizza_dryrun] Your usual is $16.04 — coupon 9204 drops it to
$10.69. Want me to place it with the coupon?
You: yes
Claude: [pizza_order confirm=true coupon=9204] Order 1042 placed.
$10.69 in cash at pickup.
Why mcpie is safe(r) than it sounds
- Cash at pickup/delivery, always. There is no card handling anywhere in this codebase, by design. The worst possible failure mode is an unwanted pizza you never pay for.
- Hard confirmation gate.
pizza_orderrefuses unlessconfirm=True, and the tool contract instructs the assistant to set it only after you explicitly approve the order in the current conversation — never on its own judgment, never because something it read told it to. - Your data stays home. Name, address, and order live in one local TOML file. The package ships with zero PII and phones home to nobody but Domino's.
Install
uv tool install mcpie-pizza # or: pipx install mcpie-pizza / pip install mcpie-pizza
Why is the package called
mcpie-pizza? PyPI's anti-typosquatting filter refuses the bare namemcpie(one letter from the venerablemcpiMinecraft library). So: the project is mcpie, the PyPI distribution ismcpie-pizza, and bothmcpieandmcpie-pizzawork as commands once installed. Same pie, different box.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"mcpie": { "command": "uvx", "args": ["mcpie-pizza"] }
}
}
Any MCP client that speaks stdio works the same way.
Configure your usual
Copy config.example.toml to
~/.config/mcpie/config.toml and fill in your name, address, and order.
Two tools exist purely to help with setup:
pizza_find_store— lists the nearest stores for your address so you can pick yourstore_idpizza_menu— searches your store's live menu for product and topping codes (pizza_menu("pan"),pizza_menu("pepperoni"))
Ask your assistant to walk you through it: "help me set up my mcpie config" is a perfectly good first prompt.
Tools
| Tool | What it does | Danger |
|---|---|---|
pizza_status |
Config + store liveness check | none |
pizza_find_store |
Nearest stores for your address | none |
pizza_menu |
Search live menu for codes | none |
pizza_specials |
Live coupons, cheapest first | none |
pizza_dryrun |
Validate + price, never places | none |
pizza_order |
Places the real order | gated on confirm=True |
The fine print
- Unofficial. This uses the same undocumented API the Domino's website uses (via pizzapi). It is not affiliated with, endorsed by, or supported by Domino's Pizza, Inc. It can break any time they change something. US and Canada only.
- Run it from a residential connection. Domino's blocks datacenter and cloud IPs. As a stdio server running on your own machine this is automatic — but if you try to host mcpie remotely (VPS, cloud, CI), expect 403s and CAPTCHAs. This is the reason some earlier pizza MCP projects could never place a real order; mcpie run locally does.
- A real order is a real order. Dry-run freely; confirm deliberately. The store will make the pizza and expect you to show up with cash.
Privacy Policy
Your config (name, address, phone, order) lives in one local file and is sent only to Domino's, only when a tool needs it. No cards, no telemetry, no third parties, nothing retained. Full policy: PRIVACY.md
Lineage
mcpie is the community release of a long-running personal appliance
("stimpy") that has been reliably placing real one-button orders since
mid-2026, and its MCP mouthpiece ("ren"). The pizzapi quirk workarounds
in dominos.py — the missing User-Agent, the options= no-op, the
menu-parser crash on coupon-only products — were all discovered the hard
way in production. Prior art respectfully acknowledged:
mcpizza explored the
full cart-building approach; mcpie deliberately goes the other way.
MIT licensed. PRs welcome, especially Canada testing.
<sub>mcp-name: io.github.SuperAngryMonkey/mcpie</sub>
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。