Skip to main content

A Model Context Protocol server for interacting with TastyTrade brokerage accounts

Project description

tasty-agent: A TastyTrade MCP Server

A Model Context Protocol server for TastyTrade brokerage accounts. Enables LLMs to monitor portfolios, analyze positions, and execute trades.

Installation

uvx tasty-agent

Authentication

Set up credentials (stored in system keyring):

uvx tasty-agent setup

Or use environment variables:

  • TASTYTRADE_USERNAME
  • TASTYTRADE_PASSWORD
  • TASTYTRADE_ACCOUNT_ID (optional)

MCP Tools

Account & Portfolio

  • get_balances - Account balances and buying power
  • get_positions - All open positions with current values
  • get_live_orders - Currently active orders
  • get_net_liquidating_value_history - Portfolio value history (1d, 1m, 3m, 6m, 1y, all)
  • get_history - Transaction history (default: last 90 days)

Order Management

  • place_order - Place new orders (single/multi-leg strategies)
    • Parameters: legs, order_type (Limit/Market), time_in_force (Day/GTC/IOC), price, dry_run
  • delete_order - Cancel orders by ID
  • get_order - Get order details by ID
  • replace_order - Modify existing orders

Market Data

  • get_option_chain - Option chain with filtering by expiration, strikes, type
  • get_quote - Real-time quotes via DXLink streaming
  • get_market_metrics - IV rank, percentile, beta, liquidity for multiple symbols
  • check_market_status - Market hours and next open time

Order Format

Orders use JSON leg format:

[
  {
    "symbol": "AAPL",
    "quantity": "100",
    "action": "Buy",
    "instrument_type": "Equity"
  }
]

Actions: Equity: Buy/Sell | Options: Buy/Sell to Open/Close Option Symbols: Auto-normalized from OCC to OSI format

Key Features

  • Multi-leg strategies with complex option spreads
  • Real-time streaming quotes via DXLink WebSocket
  • Dry-run testing for all order operations
  • Automatic symbol normalization for options
  • Fresh data always from TastyTrade API

Usage with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "tastytrade": {
      "command": "uvx",
      "args": ["tasty-agent"]
    }
  }
}

Examples

"Get my account balances and current positions"
"Show AAPL option chain for next Friday expiration"
"Get real-time quote for SPY"
"Place dry-run order: buy 100 AAPL shares at market"
"Cancel order 12345"

Multi-leg Order Example

# Iron condor strategy
legs = [
  {"symbol": "SPY240315P00480000", "quantity": "1", "action": "Sell to Open", "instrument_type": "Equity Option"},
  {"symbol": "SPY240315P00475000", "quantity": "1", "action": "Buy to Open", "instrument_type": "Equity Option"},
  {"symbol": "SPY240315C00520000", "quantity": "1", "action": "Sell to Open", "instrument_type": "Equity Option"},
  {"symbol": "SPY240315C00525000", "quantity": "1", "action": "Buy to Open", "instrument_type": "Equity Option"}
]

Development

Debug with MCP inspector:

npx @modelcontextprotocol/inspector uvx tasty-agent

License

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tasty_agent-1.0.0.tar.gz (46.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

tasty_agent-1.0.0-py3-none-any.whl (9.0 kB view details)

Uploaded Python 3

File details

Details for the file tasty_agent-1.0.0.tar.gz.

File metadata

  • Download URL: tasty_agent-1.0.0.tar.gz
  • Upload date:
  • Size: 46.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.10

File hashes

Hashes for tasty_agent-1.0.0.tar.gz
Algorithm Hash digest
SHA256 915e5c6071d6c5d58c0f8cb6b448d258980526489579f1b046693db1e92f55f4
MD5 0918114715627ba628c150a037995a09
BLAKE2b-256 f8a26bf7af291e22d79602718dc89f7f0268012708ef33eab291298ae94e323b

See more details on using hashes here.

File details

Details for the file tasty_agent-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: tasty_agent-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 9.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.10

File hashes

Hashes for tasty_agent-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f3d1713f97f324bde1697d5a437d79bfbc1c2b001173312387826e3db6776f67
MD5 960475576e406e535db9b80337a2f5d6
BLAKE2b-256 6970428ea177c0a8a817dbe015f682d13f8c3cd7347b6a4bcc77db747905746e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page