pyhood-mcp
Connect your Robinhood account to Claude Code (or any MCP client) for conversational portfolio management and automated trading.
README
pyhood-mcp
Model Context Protocol (MCP) server for Robinhood trading via pyhood
Connect your Robinhood account to Claude Code (or any MCP client) for conversational portfolio management and automated trading.
Features
- ๐ Portfolio monitoring (positions, gains/losses, buying power)
- ๐ Real-time quotes and market data
- ๐ Stock order placement (market, limit, stop orders)
- ๐ Order history and management
- ๐ Historical price data for technical analysis
- ๐ฐ Options chain data and expirations
- ๐ข Fundamental data (market cap, PE ratio, etc.)
Installation
Prerequisites
- Python 3.10+
- A Robinhood account
- Claude Code (or any MCP-compatible client)
Install dependencies
pip install pyhood mcp
Download the server
# Clone this repo
git clone https://github.com/YOUR_USERNAME/pyhood-mcp.git
cd pyhood-mcp
# Or just download pyhood_mcp_server.py
curl -O https://raw.githubusercontent.com/YOUR_USERNAME/pyhood-mcp/main/pyhood_mcp_server.py
chmod +x pyhood_mcp_server.py
Setup
1. Authenticate with Robinhood
First, create a session (handles 2FA):
python3 -c "import pyhood; pyhood.login(username='YOUR_EMAIL', password='YOUR_PASSWORD')"
This creates a cached session in ~/.pyhood/session.json.
2. Configure Claude Code
Add to your ~/.claude/settings.json:
{
"mcpServers": {
"pyhood": {
"command": "python3",
"args": ["/path/to/pyhood_mcp_server.py"],
"env": {
"ROBINHOOD_USERNAME": "your_email@example.com",
"ROBINHOOD_PASSWORD": "your_password"
}
}
}
}
Or set environment variables in your shell:
export ROBINHOOD_USERNAME="your_email@example.com"
export ROBINHOOD_PASSWORD="your_password"
3. Restart Claude Code
The pyhood MCP server will now be available in Claude Code.
Usage
In Claude Code
What's my portfolio performance today?
Get a quote for NVDA
Place a market order to buy 10 shares of AAPL
Show me my recent order history
Get historical data for TSLA over the past month
Available Tools
| Tool | Description |
|---|---|
get_portfolio |
Portfolio summary with all positions |
get_positions |
List all current positions |
get_quote |
Real-time quote for a symbol |
get_quotes |
Quotes for multiple symbols |
get_buying_power |
Available cash balance |
place_order |
Place buy/sell orders |
get_stock_orders |
Recent order history |
cancel_order |
Cancel a pending order |
cancel_all_stock_orders |
Cancel all pending orders |
get_order |
Check status of a specific order |
get_stock_historicals |
Historical price data |
get_fundamentals |
Company fundamentals |
get_earnings |
Earnings dates and estimates |
get_options_chain |
Options data for a symbol |
get_options_expirations |
Available option expirations |
Security
โ ๏ธ Important Security Notes:
- Never commit your Robinhood credentials to git
- The session cache (
~/.pyhood/session.json) contains sensitive tokens - Use environment variables for credentials when possible
- This server runs locally and communicates only with Robinhood's API
Pattern Day Trading (PDT)
If your account is <$25k, you're limited to 3 day trades per rolling 5-day period. Be careful with automated trading strategies. See FINRA PDT rules.
Dependencies
Disclaimer
This software is for educational purposes only. Trading stocks involves risk.
- You are responsible for all trades executed through this tool
- No warranty or guarantee of fitness for any purpose
- The authors are not liable for any financial losses
- Always verify orders before execution
- Use at your own risk
Robinhoodยฎ is a trademark of Robinhood Markets, Inc. This project is not affiliated with or endorsed by Robinhood.
Contributing
Contributions welcome! Please:
- Fork the repo
- Create a feature branch
- Submit a pull request
License
MIT License - see LICENSE file for details
Related Projects
- autonomous-trading-agent - Autonomous trading agent using this MCP server
- pyhood - The underlying Robinhood API client
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.