uber-mcp
Related Servers
Alternatives to uber-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with the Uber API for ride management, including requesting rides, obtaining price and time estimates, and tracking active trip status. It supports comprehensive journey features such as viewing ride history, cancelling requests, and rating drivers through a secure OAuth 2.0 integration.MIT
- AlicenseAqualityCmaintenanceEnables an AI agent to retrieve ride quotes, book and track rides, cancel, manage scheduled and two-stop trips, and work with saved locations and addresses.19MIT
- AlicenseBqualityCmaintenanceEnables end-to-end ride-booking workflows, including pickup and destination selection, ride estimates, solo or ShareMatch shared rides, driver tracking with live ETAs, trip management, payments, receipts, saved places, and safety/support tools.39MIT
- FlicenseAqualityDmaintenanceAllows AI assistants to browse menus, manage carts, and place orders on Uber Eats through natural language commands.343-
- AlicenseAqualityDmaintenanceAn MCP server that enables AI assistants to book and manage Uber rides, including getting price estimates, requesting rides, checking ride status, and canceling rides.614 npm16ISC
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to search for cabs, view prices, and book rides through the open Beckn Protocol by connecting to Beckn-compliant mobility providers like Namma Yatri and ONDC.-
TDQS
Scored across 13 tools
The set is split cleanly along real axes: now vs. future vs. read-only pricing (uber_request_ride / uber_reserve_ride / uber_ride_options), cancel now vs. cancel future (uber_cancel_ride / uber_cancel_reservation), list vs. single trip vs. reservation (uber_trips / uber_trip / uber_reservation), and auth vs. profile vs. server health (uber_connect / uber_account / uber_status). A couple of near-homographs remain — uber_reservation vs. uber_reserve_ride, and uber_status vs. uber_ride_status — where an agent could plausibly reach for the wrong tool before reading the description. Descriptions do explicitly cross-reference and redirect, which rescues most of that overlap.
All tools share a uniform uber_ prefix and snake_case, and there is an implicit and mostly respected convention: verb-led names for mutations (request_ride, reserve_ride, cancel_ride, cancel_reservation, connect) and bare nouns for reads (account, places, trips, trip, status, reservation). The deviations are the noun forms uber_ride_options and uber_ride_status, which mix the noun convention with an extra qualifier, and the confusingly similar reserve_ride/reservation pair.
Thirteen tools for a rideshare domain of this breadth is well-scoped, with each tool owning a distinct action or resource. Nothing looks padded: even the auth and diagnostic tools (uber_connect, uber_status) earn their place because every booking tool can fail with not_signed_in or a cap.
The core lifecycle is covered end to end: discover places, compare products and fares, book now or schedule, poll live trip state, cancel either kind, and review history. The main gaps are post-ride actions — no rating, tipping, receipt/expense retrieval, lost-item or support flows — and no way to modify an existing reservation other than cancel and rebook. These are workarounds rather than dead ends, since cancel+reserve covers the modification case.