Strider Labs Uber MCP

by markswendsen-code

Not rated
GitHub

About

MCP server for Uber - let AI agents book rides, get fare estimates, and track trips

Details

Author
markswendsen-code
Categories
Other, API

Setup

Install Strider Labs Uber MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/markswendsen-code/mcp-uber

Follow the installation instructions in the repository README, then restart your MCP client.

MCP server connector for Uber ride-sharing — request rides, get fare estimates, and track trips via browser automation.

Add to yourclaude_desktop_config.json:

{ "mcpServers": { "uber": { "command": "npx", "args": ["@striderlabs/mcp-uber"] } } }

Check Uber authentication and session status, including the current pickup/destination if set.

Authenticate with Uber using email/phone and password via browser automation.

Note:Uber often requires phone OTP verification. If OTP is triggered, run withheadless: falseto complete verification in the visible browser window, then callloginagain.

Set the pickup location for a ride request. Persists across tool calls.

Set the destination for a ride request. Persists across tool calls.

Get fare estimates for all available ride types between pickup and destination.

Note:Set pickup and destination first withset_pickup/set_destination, or provide them directly as parameters.

Get available ride types (UberX, Comfort, XL, Black, etc.) with pricing and ETAs for the current route.

Request an Uber ride. Returns a confirmation preview by default — doesnotautomatically confirm.

Warning:Settingconfirm: truewill attempt to place a real ride request. Make sure pickup, destination, and ride type are correct before confirming.

Get the status of your current or most recent Uber ride.

Cancel a pending or active Uber ride request.

Note:A cancellation fee may apply if a driver has already been assigned. Review the cancellation policy before confirming.

Agents can use this connector to autonomously request, track, and manage Uber rides on behalf of their human. Example agent flow:

Agent:"I need to get to JFK Airport. What's the cheapest ride available?"
- Callset_pickupwith the user's current location
- Callset_destinationwith "JFK Airport"
- Callget_fare_estimateto compare UberX, Comfort, XL pricing
- Return a summary of options and estimated wait times

Agent:"Request the UberX ride."
- Callrequest_ridewithride_type: "UberX"andconfirm: true
- Receive a confirmation with driver ETA
- Store the ride ID for tracking
- Autonomously callget_ride_statusat intervals to keep the user informed

This connector is designed to work in autonomous personal assistant scenarios where the agent has persistent access to the user's Uber account and makes ride decisions based on context (location, cost, time, preferences).

1. login → Authenticate with Uber 2. set_pickup → "Times Square, New York, NY" 3. set_destination → "JFK Airport, Queens, NY" 4. get_fare_estimate → Review prices for UberX, Comfort, XL, etc. 5. request_ride → Preview the ride (confirm: false) 6. request_ride → confirm: true to place the request 7. get_ride_status → Track your driver 8. cancel_ride → Cancel if needed (confirm: true)

- Transport:stdio (MCP standard)
- Browser:Chromium via Playwright with stealth patches
- Stealth:Patchesnavigator.webdriver, spoof plugins/languages, remove automation markers
- Geolocation:Defaults to New York City (40.7128, -74.006)
- User Agent:Chrome 120 on macOS

- OTP/Captcha:Uber may require phone OTP or CAPTCHA during login. Useheadless: falseto handle these manually.
- Fare Estimates:Available without login via uber.com/global/en/price-estimate/
- Ride Requests:Require an active logged-in session.
- Cancellation Fees:Uber may charge a fee if you cancel after a driver is assigned.
- Mobile App:Uber is primarily a mobile app. The web interface (riders.uber.com) is used for automation, which may have different features than the mobile app.

Transaction-complete hotel booking over MCP — 300K+ properties, real hotel confirmation numbers, loyalty points, secure checkout. Hotels are merchant of record. Builders set their own booking fee via Stripe Connect. Built on proven distribution infrastructure.

Apigene MCP Gateway is the runtime layer that connects AI agents to APIs and MCP servers via Model Context Protocol.

An MCP server for fetching verifiable random numbers from the drand network.

One MCP server for AI agents to use any tools reliably at any scale

Global postal code lookups, validation, and city search for 70+ countries. Sub-10ms responses.

Connect to any financial, utility, billing accounts; retrieve balance, transactions, payment and identity data instantly.

One API key, dozens of capabilities for your AI agent. Zero provider auth.

Hosted remote MCP server with managed OAuth for a growing list of 15+ toolkits, including Google Workspace, Last.fm, MusicBrainz, Fitbit, Oura, Kalshi, and Polymarket.

Static MCP discovery card for x402 spend-policy, paid MCP launch guidance, seller checkout repair, and agent-payment safety APIs.

MCP server for 402 Index: discover 15,000+ paid API endpoints across L402, x402, and MPP

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.