loading…
Search for a command to run...
loading…
Tastyworks API integration to handle trading activities on Tastytrade
Tastyworks API integration to handle trading activities on Tastytrade
A Model Context Protocol server for TastyTrade brokerage accounts. Enables LLMs to monitor portfolios, analyze positions, and execute trades. Features automated IV analysis prompts and built-in rate limiting (2 requests/second) to prevent API errors.
OAuth Setup:
account_overview(include=["balances","positions"]) - Account balances (including net liquidating value) and open positions.get_quotes(instruments, timeout=10.0) - Real-time quotes for stocks, options, futures, and indices via DXLink streamingget_greeks(options, timeout=10.0) - Greeks (delta, gamma, theta, vega, rho) for options via DXLink streamingget_gex(symbol, expiration_date, timeout=60.0) - Gamma Exposure analysis: net GEX, gamma regime, flip level, call/put walls, and top strikesget_market_metrics(symbols) - IV rank, percentile, beta, liquidity for multiple symbolsmarket_status(exchanges=['Equity']) - Market hours, status, holidays, and current NYC time ('Equity', 'CME', 'CFE', 'Smalls')search_symbols(symbol, limit=10) - Search for symbols by name/tickerget_history(type, days=None, underlying_symbol=None, transaction_type=None, page_offset=0, limit=25) - Transaction history (type="transactions", default 90 days) or order history (type="orders", default 7 days). Paginated — use page_offset and limit for large result sets. Filter transactions by "Trade" or "Money Movement".place_order(legs, target_value=None, chase=true, time_in_force="Day", dry_run=false) - Place multi-leg orders with quote-derived mid pricing only. The tool fetches live quotes for the exact resolved instruments, computes the signed net mid, validates the final limit against bid/ask guardrails, and optionally sizes quantity from target_value.target_value=50000 sizes an equity or equity-option order from quote-derived pricing. With target_value, leg quantity is a ratio and usually omitted/defaults to 1.chase=true enables bounded repricing after placement: wait 10 seconds, check whether the order is still live, then recalculate from fresh exact-instrument quotes and move 1 valid price tick closer to fill. Defaults are 10 seconds, 10 reprices max, 1 tick per reprice.Buy to Open, Buy to Close, Sell to Open, or Sell to Close; futures use Buy or Sell.replace_order(order_id) - Reprice an existing live order at the current quote-derived mid.cancel_order(order_id) - Cancel an order.list_orders() - Get all live orders.watchlist(action, ...) - Unified watchlist management:action="list" - No name returns compact watchlist metadata (name, group, symbol_count); with name, returns compact symbol entries.action="add" - Add symbols to a watchlist (creates if doesn't exist)action="remove" - Remove symbols from a watchlistaction="delete" - Delete a watchlistAdd to your MCP client configuration (e.g., claude_desktop_config.json):
{
"mcpServers": {
"tastytrade": {
"command": "uvx",
"args": ["tasty-agent"],
"env": {
"TASTYTRADE_CLIENT_SECRET": "your_client_secret",
"TASTYTRADE_REFRESH_TOKEN": "your_refresh_token",
"TASTYTRADE_ACCOUNT_ID": "your_account_id"
}
}
}
}
Deploy as a remote MCP server on Modal with proxy auth:
pip install modal && modal setup
# Create secrets
modal secret create tasty-agent-secrets \
TASTYTRADE_CLIENT_SECRET=your_secret \
TASTYTRADE_REFRESH_TOKEN=your_token
# Create a proxy auth token at https://modal.com/settings/proxy-auth-tokens
# Export your workspace host
export MODAL_HOST=<workspace>--tasty-agent-mcp-server.modal.run
# Deploy
modal deploy examples/modal_deploy.py
Clients authenticate with Modal-Key and Modal-Secret headers. See examples/modal_deploy.py.
Tagged releases can also auto-deploy the Modal app. Configure these GitHub settings once:
MODAL_TOKEN_ID, MODAL_TOKEN_SECRETMODAL_HOSTTASTY_AGENT_SECRET_NAME if you do not use the default tasty-agent-secretsAfter that, pushing a release tag like v4.1.2 will publish to PyPI and deploy Modal with tasty-agent==4.1.2.
Connect to a remote tasty-agent and call tools directly:
# List all tools
uv run examples/mcp_client.py
# Call a tool
uv run examples/mcp_client.py market_status
uv run examples/mcp_client.py get_market_metrics '{"symbols": ["AAPL", "SPY"]}'
See examples/mcp_client.py for the full client code.
"Get my account balances and current positions"
"What's my net liquidating value?"
"Get real-time quotes for SPY and AAPL"
"Get quotes for TQQQ C option with strike 100 expiring 2026-01-16"
"Get Greeks for AAPL P option with strike 150 expiring 2024-12-20"
"Show GEX analysis for SPY options expiring 2026-04-03"
"Buy to open 100 AAPL shares at mid"
"Buy to open 17 TQQQ calls, strike 100, exp 2026-01-16"
"Buy $50K of TSLA calls, strike 300, exp 2026-01-16"
"Buy TSLA calls, strike 300, exp 2026-01-16, and chase if not filled"
"Place a call spread: buy to open AAPL 150C and sell to open AAPL 155C, both exp 2024-12-20"
"Buy 1 /ESM26 future at mid"
"Reprice order 12345 at mid"
"Cancel order 12345"
"Show my live orders"
"Get my trading history from January"
"Get my order history for SPY"
"Get my private watchlists"
"Add TSLA and NVDA to my tech watchlist"
# Run tests
uv run pytest
# Interactive chat client (requires .env with credentials + OPENAI_API_KEY)
uv run examples/chat.py
# Background trading bot
uv run examples/background.py "Check portfolio and rebalance" --hourly
# Debug with MCP inspector
npx @modelcontextprotocol/inspector uvx tasty-agent
MIT
Добавь это в claude_desktop_config.json и перезапусти Claude Desktop.
{
"mcpServers": {
"ferdousbhai-tasty-agent": {
"command": "npx",
"args": []
}
}
}