Uber MCP server for AI agents
Let Claude, ChatGPT or your own agent read Uber: 1 typed function through one MCP server. No Uber API key needed.
- Site
- drivers.uber.com
- Functions
- 1
- Sign-in
- For account actions
- Works with
- MCP, HTTP, Node, Python
Connect
Just Uber
An MCP server for Uber alone, with one tool per function. Paste it into Claude, ChatGPT, Cursor or any MCP client as a remote server.
https://api.bowmark.ai/mcp/site/uberEvery site
One MCP server for Uber and every other site Bowmark covers. Your agent looks up what it needs and calls it.
https://api.bowmark.ai/mcpSet it up in your clientBoth need a Bowmark API key. The quickstart gets you one and a first result in a few minutes. Functions that need a login use the person's own account: how sign-in works.
Functions
Open a function to see its arguments, what it returns and how to call it.
Read 1
getDriverEarningsReturns a signed-in driver's earnings summary for a specified week: trip count and net earnings total.Arguments
Name Type Required weekOffsetnumberNo Returns
DriverEarningsinterface DriverEarnings { weekStart: string; tripCount: number; netEarnings: number; }HTTP endpoint
POST https://api.bowmark.ai/v1/sites/uber/getDriverEarningsCall it
import { bowmark } from "@bowmark/web"; const result = await bowmark.providers.uber.getDriverEarnings(0);import asyncio from bowmark_web import bowmark result = asyncio.run(bowmark.providers.uber.getDriverEarnings(0))curl -X POST https://api.bowmark.ai/v1/sites/uber/getDriverEarnings \ -H "Authorization: Bearer $BOWMARK_API_KEY" \ -H "Content-Type: application/json" \ -d '{"weekOffset":0}'// The body of a run: the MCP run tool, or POST /v1/run return await bowmark.providers.uber.getDriverEarnings(0);
Use it from code
- Node
npm i @bowmark/web - Python
pip install bowmark-web - HTTP
POST /v1/sites/uber/<function> - OpenAPI
/v1/sites/uber/openapi.json