MCP candidate - DoorDash publishes no MCP server
DoorDash publishes NO Model Context Protocol server. Nothing on developer.doordash.com mentions MCP (415 sitemap URLs checked, zero matches), no /mcp endpoint exists on openapi.doordash.com, and every DoorDash MCP server on the registries - amannm/doordash-mcp, SpunkySarb/doordash-mcp, jordandalton's Drive server, @striderlabs/mcp-doordash - is a third-party wrapper, two of which drive DoorDash's unpublished consumer GraphQL through a browser session rather than the documented API. DoorDash does run MCP internally: its engineering blog describes a centralized gateway giving internal AI agents access to internal APIs and SaaS tools, which is an employee surface, not a partner one. The tools below are a CANDIDATE set derived from the operations DoorDash does publish, so an implementer has a starting shape. Nothing here is served by DoorDash.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
doordash_create_delivery_quote— Price and serviceability check for a pickup/dropoff pair. Creates no delivery.doordash_accept_delivery_quote— Commit a previously created quote into a real delivery, optionally with a tip.doordash_create_delivery— Create a delivery in one call, skipping the quote step.doordash_get_delivery—doordash_update_delivery—doordash_cancel_delivery— Reversal for create_delivery. Only works before a Dasher is assigned; afterwards DoorDash creates a return delivery billed at 60% of the original fee.doordash_check_serviceability—doordash_autocomplete_address—doordash_get_substitution_recommendation—doordash_list_businesses—doordash_list_stores—doordash_create_store—doordash_get_store_menu—doordash_confirm_order—doordash_cancel_order—doordash_activate_item—doordash_request_report—doordash_get_report_link—
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.