Uber Eats MCP Server
Uber Eats order and data interaction capabilities for AI assistants.
Data last scanned last week · Reviewed last month
Overview
The Uber Eats MCP Server provides a proof-of-concept implementation for connecting LLM applications to Uber Eats. It utilizes Python and requires integration with an LLM provider, such as Anthropic, to function within an AI-driven workflow. The setup leverages Playwright to handle interactions through the browser. Users can configure the environment via a standard .env file to supply necessary API keys. Debugging is supported through the official MCP inspector tool.
Our verdict
This project holds a high-risk profile with a security score of 20/100. Because it is a community-maintained proof-of-concept that has not been updated in over 500 days and lacks a defined software license, it is not recommended for production use or sensitive environments. The lack of an established maintenance lifecycle and the absence of clear legal usage terms present significant barriers for reliable adoption.
- Minimalist design with zero direct dependencies
- Includes documentation for setup and debugging workflows
- Project inactive for over 515 days
- Lacks an open-source license
- High security risk due to lack of editorial review
- Not maintained by an official vendor
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| ChatGPT | ||||
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf |
Frequently asked questions
›What are the software environment prerequisites?
You must have Python 3.12 or higher installed and an active Anthropic API key or another supported LLM provider.
›How do I configure my credentials?
You need to add your API key to the .env file in the project directory.
›Are there specific browser dependencies required?
Yes, you must run the Playwright install command after installing the package requirements.
›How can I troubleshoot or debug the server?
You can use the MCP inspector tool by running the command uv run mcp dev server.py.
›Are there any constraints on output I should be aware of?
Browser output is disabled because the server uses stdio as the MCP transport.
Badge
Maintain this server? Add the live badge to your README.