Uber Eats
ericzakariasson/uber-eats-mcp-server
The Uber Eats MCP Server provides a proof-of-concept integration between large language models and Uber Eats functionality through the Model Context Protocol. The server enables LLM applications to interact with Uber Eats using browser automation via Playwright, allowing users to leverage AI assistants to access food delivery capabilities programmatically. This integration solves the problem of connecting AI applications to real-world services by establishing a standardized protocol bridge between LLMs and external web-based platforms.
- GitHub stars
- 224
- last updated
- Feb 7, 2026
Sponsors
Readme
Uber Eats MCP Server
This is a POC of how you can build an MCP servers on top of Uber Eats
https://github.com/user-attachments/assets/05efbf51-1b95-4bd2-a327-55f1fe2f958b
What is MCP?
The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external tools.
Prerequisites
- Python 3.12 or higher
- Anthropic API key or other supported LLM provider
Setup
-
Ensure you have a virtual environment activated:
uv venv source .venv/bin/activate # On Unix/Mac -
Install required packages:
uv pip install -r requirements.txt playwright install -
Update the
.envfile with your API key:ANTHROPIC_API_KEY=your_openai_api_key_here
Note
Since we're using stdio as MCP transport, we have disable all output from browser use
Debugging
You can run the MCP inspector tool with this command
uv run mcp dev server.py