Fyers MCP Server
Enables Claude to interact with the Fyers trading platform for portfolio management, order placement, market data retrieval, and automated OAuth authentication for Indian stock markets.
README
Fyers MCP Server
MCP (Model Context Protocol) server for Fyers API v3 with automated OAuth authentication
A comprehensive MCP server that enables Claude Desktop to interact with Fyers trading platform through a secure, automated authentication flow. Supports all major trading operations including portfolio management, order placement, and real-time market data.
š¬ Demo
<video src="https://github.com/quantabox/fyers-mcp-server/assets/fyers-mcp.mp4" width ="300"/>
⨠Features
š Smart Authentication
- One-click OAuth flow with automatic browser handling
- Persistent token storage in
.envfile - Auto-refresh capabilities with session management
š Complete Trading Toolkit
- Portfolio Management: Holdings, positions, funds, profile
- Order Management: Place, modify, cancel orders
- Market Data: Real-time quotes for multiple symbols
- Order History: Complete order and trade book
š Production Ready
- Full error handling with detailed error messages
- Type safety with parameter validation
- Comprehensive logging for debugging
- Claude Desktop integration with simple configuration
š Quick Start
Prerequisites
- Python 3.10 or higher
- Claude Desktop installed
- Fyers Trading Account with API access
1. Installation
# Clone the repository
git clone https://github.com/quantabox/fyers-mcp-server.git
cd fyers-mcp-server
# Install dependencies using uv (recommended)
curl -LsSf https://astral.sh/uv/install.sh | sh
uv sync
# Or install with pip
pip install .
2. Get Fyers API Credentials
-
Create Fyers API App:
- Visit Fyers API Dashboard
- Create a new app with redirect URI:
http://localhost:8080/ - Note down your
App IDandSecret Key
-
Configure Environment:
cp .env.example .envEdit
.envfile:FYERS_CLIENT_ID=YOUR_APP_ID-100 # e.g., ABC123XYZ-100 FYERS_SECRET_KEY=YOUR_SECRET_KEY # Secret from Fyers app FYERS_REDIRECT_URI=http://localhost:8080/
3. Configure Claude Desktop
Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"fyers-mcp-server": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/fyers-mcp-server",
"python",
"fyers_mcp_complete.py"
],
"env": {
"PYTHONWARNINGS": "ignore"
}
}
}
}
4. First Run
- Restart Claude Desktop
- Authenticate: In Claude, type:
authenticate - Browser will open ā Login to Fyers ā Automatic token capture
- Start trading: All 11 tools are now available!
š ļø Available Tools
Authentication & Profile
authenticate()- One-click OAuth authenticationcheck_auth_status()- Verify current authenticationget_profile()- User profile information
Portfolio & Funds
get_funds()- Account balance and margin detailsget_holdings()- Portfolio holdings with P&Lget_positions()- Current trading positions
Orders & Trading
place_order(symbol, quantity, order_type, side, ...)- Place new ordersmodify_order(order_id, quantity, limit_price, ...)- Modify existing orderscancel_order(order_id)- Cancel pending ordersget_orders()- Order history and status
Market Data
get_quotes(symbols)- Real-time quotes for multiple symbols
š Usage Examples
Portfolio Analysis
# Check account balance
get_funds()
# View all holdings with P&L
get_holdings()
# Check current positions
get_positions()
Order Management
# Place a market order
place_order("NSE:SBIN-EQ", 10, "MARKET", "BUY")
# Place a limit order
place_order("NSE:RELIANCE-EQ", 5, "LIMIT", "BUY", limit_price=2500)
# Modify an order
modify_order("ORDER_ID", quantity=15, limit_price=2550)
# Cancel an order
cancel_order("ORDER_ID")
Market Data
# Get live quotes
get_quotes("NSE:SBIN-EQ,NSE:RELIANCE-EQ,NSE:TCS-EQ")
š§ Configuration Options
Order Types
MARKET- Market order (immediate execution)LIMIT- Limit order (execute at specific price)STOP- Stop loss orderSTOPLIMIT- Stop limit order
Product Types
MARGIN- Margin trading (intraday with leverage)CNC- Cash and Carry (delivery)INTRADAY- Intraday tradingBO- Bracket OrderCO- Cover Order
Validity Options
DAY- Valid for current trading dayIOC- Immediate or CancelGTD- Good Till Date
š Troubleshooting
Common Issues
1. Authentication Failed
# Check credentials in .env file
cat .env | grep FYERS
# Verify app configuration at https://myapi.fyers.in/dashboard/
2. Claude Desktop Connection Issues
# Test MCP server directly
cd /path/to/fyers-mcp-server
uv run python fyers_mcp_complete.py
# Check Claude Desktop logs (macOS)
tail -f ~/Library/Logs/Claude/mcp.log
3. Order Placement Errors
- Verify symbol format:
NSE:SYMBOL-EQfor equity - Check market hours (9:15 AM - 3:30 PM IST)
- Ensure sufficient funds/margin
Debug Mode
Enable detailed logging:
export LOG_LEVEL=DEBUG
uv run python fyers_mcp_complete.py
š§ Development
Project Structure
fyers-mcp-server/
āāā fyers_mcp_complete.py # Main MCP server
āāā pyproject.toml # Dependencies
āāā .env.example # Environment template
āāā claude_config.json # Claude Desktop config
āāā README.md # This file
Adding New Features
- Fork the repository
- Create feature branch:
git checkout -b feature/new-tool - Add MCP tool: Use
@mcp.tool()decorator - Test with Claude Desktop
- Submit pull request
Testing
# Install development dependencies
uv sync --dev
# Run tests
uv run pytest
# Type checking
uv run mypy fyers_mcp_complete.py
š API Reference
Authentication Flow
graph TD
A[Claude: authenticate] --> B[Generate Auth URL]
B --> C[Open Browser]
C --> D[User Login]
D --> E[Auth Code Capture]
E --> F[Exchange for Token]
F --> G[Store in .env]
G --> H[Ready for Trading]
Error Handling
All functions return standardized responses:
- ā Success: Clear confirmation with relevant data
- ā Error: Detailed error message with troubleshooting hints
š¤ Contributing
We welcome contributions! Please see our Contributing Guidelines for details.
Areas for Contribution
- WebSocket real-time data streaming
- Advanced order types (OCO, Iceberg)
- Portfolio analytics and reporting
- Options chain analysis tools
- Risk management features
š License
This project is licensed under the MIT License - see the LICENSE file for details.
ā ļø Disclaimer
This software is for educational and development purposes. Trading involves financial risk. Users are responsible for their trading decisions and should thoroughly test in demo environments before live trading.
š Links
š Status
- Current Version: 1.0.0
- API Compatibility: Fyers API v3.1.7
- Python Support: 3.10+
- Tools Available: 11/11 ā
- Production Ready: Yes ā
<p align="center"> <strong>Made with ā¤ļø for the trading community</strong><br> <sub>Enable algorithmic trading with Claude's intelligence</sub> </p>
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
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.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.