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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.