DoorDash over text
Enables ordering DoorDash via Poke over text, with tools for restaurant discovery, cart management, promo application, and order submission requiring explicit user confirmation.
README
Poke × DoorDash CLI recipe
A Poke recipe that lets Poke order DoorDash for you over text,
powered by DoorDash's official dd-cli (limited beta, announced 2026-07-15 by
@andyfang).
Poke installs recipe integrations as MCP servers, so this repo is a thin MCP
bridge: Poke → tunnel → server.mjs → dd-cli → DoorDash.
Prerequisites
- dd-cli — official binary from doordash-oss/doordash-cli
(macOS Apple Silicon only). v0.2.0 tarball is downloaded + SHA256-verified in
~/Downloads/dd-cli-v0.2.0-darwin-arm64/; runbash install.shthere, thendd-cli login. Full functionality is waitlist-gated — join at https://forms.gle/gvCQZvu9C1EKA6aM6. - Node 18+, a Poke account with Kitchen access.
- Log in once via
dd-cli login(interactive; credentials go to the macOS keychain).
Run + publish
npm install
npm start # MCP server on http://localhost:3737/mcp
npm run tunnel # in a second terminal: tunnels to Poke and creates the recipe
npm run tunnel runs npx poke@latest tunnel http://localhost:3737/mcp -n "DoorDash CLI" --recipe,
which prints a shareable recipe link + QR code. (Log in first with npx poke@latest login.
The tunnel only forwards the port — start npm start before it.)
Then polish in Kitchen → your recipe. Use RECIPE.md as the recipe's instruction text — it's the agent-facing operating manual (the pattern used by published CLI-backed recipes like poke-pc). Kitchen field suggestions:
- Name: DoorDash over text
- Description: Text Poke to find food, compare deals, build a cart, and order DoorDash — with an explicit confirmation of the itemized total before anything is charged.
- inputContext: Ask the user for their delivery address (or confirm the account default), any dietary restrictions, favorite cuisines/restaurants, a typical budget per order, and default tip preference.
- prefilledFirstText: "Hey Poke — find me dinner on DoorDash. Show me a couple of good options with any deals, and always confirm the total with me before ordering."
Publishing in Kitchen makes it installable by others (and payout-eligible).
Tools exposed
Full toolset built from the complete dd-cli v0.2.0 --help tree (readable after
dd-cli login). 27 tools covering the whole surface:
- Discovery:
search_restaurants,find_nearby_stores(grocery/retail/alcohol/ convenience/pets),get_menu,find_items,restaurant_item_details,item_details,store_details,build_grocery_list - Account:
list_addresses,payment_methods,doordash_status - Cart:
cart_list(pre-flight before creating carts),cart_add_items,cart_show,cart_remove_item,cart_delete - Promos:
promo_list,promo_apply,promo_remove - Orders:
order_history,order_reorder,order_preview(relays dd-cli's--beautifysummary verbatim),order_submit,order_status,order_receipt,checkout_url(browser fallback for payment-method swaps) - Escape hatch:
dd_cliraw passthrough (loginand raworder submitblocked)
Safety, per dd-cli's own agent guidance baked into descriptions + hard guards:
order_submitcharges the default card immediately and requiresuser_confirmed=true— legitimate only after the preview was shown, the total approved, the card NAMED (brand + last4 frompayment_methods), and the Dasher tip explicitly confirmed (in cents).- Duplicate submits of the same cart are blocked in-process (dd-cli has no upstream idempotency — a resubmit would double-order).
- Cart writes auto-spaced ~8s apart (DoorDash rate limiting).
- Errors map to
not_logged_in/waitlist_pending/dd_cli_not_foundwith actionable messages the Poke agent can relay.
If the binary isn't named dd-cli on PATH, set DD_CLI_BIN.
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。