Uber Eats
A proof-of-concept Model Context Protocol server that enables LLM applications to interact with Uber Eats, allowing AI agents to browse and order food through natural language.
What is Uber Eats?
Uber Eats is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to proof-of-concept model context protocol server that enables llm applications to interact with uber eats, allowing ai agents to browse and order food through natural language.
A proof-of-concept Model Context Protocol server that enables LLM applications to interact with Uber Eats, allowing AI agents to browse and order food through natural language.
This server falls under the Business Applications category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A proof-of-concept Model Context Protocol server that enable
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx uber-eats-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Uber Eats
Uber Eats MCP Server is a proof-of-concept Python MCP server that lets LLM applications browse and interact with Uber Eats through browser automation powered by Playwright. It implements the Model Context Protocol over stdio transport, allowing AI agents to discover restaurants, view menus, and place orders on Uber Eats using natural language. This project demonstrates how to build MCP servers on top of browser-automated services that do not provide a public API, and requires an Anthropic API key for the LLM integration layer.
Prerequisites
- Python 3.12 or higher
- uv package manager installed (recommended) or pip
- An Anthropic API key set as ANTHROPIC_API_KEY environment variable
- Playwright browser automation library with browser binaries installed
- An active Uber Eats account for placing orders
Clone the repository
Clone the Uber Eats MCP server repository from GitHub.
git clone https://github.com/ericzakariasson/uber-eats-mcp-server.git
cd uber-eats-mcp-serverCreate a virtual environment and install dependencies
Set up a Python virtual environment using uv and install the required packages.
uv venv
source .venv/bin/activate
uv pip install -r requirements.txtInstall Playwright browser binaries
Install the Playwright browser drivers needed for Uber Eats browser automation.
playwright installSet your Anthropic API key
Create a .env file in the project root with your Anthropic API key.
ANTHROPIC_API_KEY=sk-ant-your-key-hereAdd to your MCP client configuration
Register the server in your Claude Desktop config to use it via the MCP protocol.
{
"mcpServers": {
"uber-eats": {
"command": "uv",
"args": ["run", "server.py"],
"cwd": "/path/to/uber-eats-mcp-server",
"env": {
"ANTHROPIC_API_KEY": "sk-ant-your-key-here"
}
}
}
}Debug with the MCP inspector
Run the MCP dev tool to inspect and test the server's tools interactively before connecting it to Claude Desktop.
uv run mcp dev server.pyUber Eats Examples
Client configuration
Claude Desktop config to run the Uber Eats MCP server via uv with the Anthropic API key.
{
"mcpServers": {
"uber-eats": {
"command": "uv",
"args": ["run", "server.py"],
"cwd": "/path/to/uber-eats-mcp-server",
"env": {
"ANTHROPIC_API_KEY": "sk-ant-your-key-here"
}
}
}
}Prompts to try
Natural language prompts to browse and order from Uber Eats through an AI agent.
- "Find pizza restaurants near me on Uber Eats that are currently open and have a rating above 4 stars."
- "Show me the menu for the top-rated sushi restaurant available on Uber Eats in my area."
- "Order two margherita pizzas and a Caesar salad from the first available Italian restaurant on Uber Eats."Troubleshooting Uber Eats
Playwright browser fails to launch or crashes
Run 'playwright install' again to ensure browser binaries are downloaded. On Linux, you may also need system dependencies: run 'playwright install-deps'.
ANTHROPIC_API_KEY not found or authentication error
Ensure the .env file is in the project root directory and contains ANTHROPIC_API_KEY=sk-ant-.... Alternatively, export it as an environment variable before starting the server.
Uber Eats login required or session lost
The server uses browser automation and may need you to log in to Uber Eats manually during the first run. Check whether the browser instance launched headlessly is blocking the login flow — you may need to set headless=False in browser.py temporarily to complete authentication.
Frequently Asked Questions about Uber Eats
What is Uber Eats?
Uber Eats is a Model Context Protocol (MCP) server that proof-of-concept model context protocol server that enables llm applications to interact with uber eats, allowing ai agents to browse and order food through natural language. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Uber Eats?
Follow the installation instructions on the Uber Eats GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Uber Eats?
Uber Eats works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Uber Eats free to use?
Yes, Uber Eats is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Uber Eats Alternatives — Similar Business Applications Servers
Looking for alternatives to Uber Eats? Here are other popular business applications servers you can use with Claude, Cursor, and VS Code.
n8n
★ 189.1kA comprehensive MCP server that provides full control over n8n automation workflows through natural language. It offers 43 tools for managing workflows, executions, credentials, and data tables, with safety features like write-mode protection and dou
LobeHub
★ 77.5k🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Jeecgboot
★ 46.4kAI 低代码平台，「低代码 + 零代码」双模式驱动：低代码一键生成前后端代码，零代码 5 分钟搭建系统，AI Skills 一句话画流程、设计表单、生成整套系统。内置 AI聊天、知识库、流程编排、MCP插件等，兼容主流大模型。引领「AI 生成 → 在线配置 → 代码生成 → 手工合并->AI修改」开发模式，消除 Java 项目 80% 的重复工作，提效而不失灵活。
CowAgent
★ 44.7kCowAgent (chatgpt-on-wechat) 是基于大模型的超级AI助理，能主动思考和任务规划、访问操作系统和外部资源、创造和执行Skills、通过长期记忆和知识库不断成长，比OpenClaw更轻量和便捷。同时支持微信、飞书、钉钉、企微、QQ、公众号、网页等接入，可选择DeepSeek/OpenAI/Claude/Gemini/ MiniMax/Qwen/GLM/LinkAI，能处理文本、语音、图片和文件，可快速搭建个人AI助理和企业数字员工。
Minds Platform
★ 39.2kPlatform dedicated to building an open foundation for applied Artificial Intelligence, designed for people seeking production-ready AI systems they can truly control, extend and deploy anywhere.
Astrbot
★ 32.8kAI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
Browse More Business Applications MCP Servers
Explore all business applications servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Uber Eats in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Uber Eats?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.