Back to MCP Catalog

TastyTrade Portfolio Manager MCP Server

Finance & FintechPython
Manage your TastyTrade brokerage account through Claude
Available Tools

get_nlv_history

Gets account net liquidating value (NLV) history for a specified time period.

time_back

get_account_balances

Retrieves current account balances including cash balance, derivative buying power, net liquidating value, and maintenance excess.

get_open_positions

Lists all currently open positions with details including symbol, type, quantity, mark price, and value.

get_transaction_history

Retrieves transaction history for a specified date range.

start_date

schedule_trade

Schedules a stock/option trade for immediate or next-market-open execution.

actionquantityunderlying_symbolstrikeoption_typeexpiration_datedry_run

list_scheduled_trades

Lists trades currently scheduled or actively processing.

cancel_scheduled_trade

Cancels a trade previously scheduled for future execution.

job_id

get_metrics

Retrieves market metrics for specified stock symbols.

symbols

get_prices

Gets current bid/ask prices for a stock or a specific option contract.

underlying_symbolexpiration_dateoption_typestrike

TastyTrade Portfolio Manager is a comprehensive tool that enables Claude to interact with your TastyTrade brokerage account. It provides capabilities for monitoring portfolio performance, analyzing positions, and executing trades directly through the TastyTrade platform. With this integration, you can check account balances, review transaction history, analyze market metrics, and even schedule and execute trades. The agent handles authentication securely through your system's keyring or environment variables, ensuring your credentials remain protected.

Overview

TastyTrade Portfolio Manager allows Claude to interact with your TastyTrade brokerage account, providing portfolio monitoring, position analysis, and trade execution capabilities.

Prerequisites

Before using this integration, you'll need:

  • Python 3.12
  • The uv package manager
  • An active TastyTrade account

Installation

  1. Install the uv package manager if you haven't already:

    curl -LsSf https://astral.sh/uv/install.sh | sh
    
  2. Add the TastyTrade Portfolio Manager to your Claude Desktop configuration by editing your claude_desktop_config.json file:

    {
      "mcpServers": {
        "tastytrade": {
          "command": "uvx",
          "args": ["tasty-agent"]
        }
      }
    }
    
  3. Restart Claude Desktop to apply the changes.

Authentication

The first time you use the TastyTrade Portfolio Manager, you'll need to set up authentication. You have two options:

Option 1: Command Line Setup (Recommended)

Run the following command to securely store your credentials in your system's keyring:

uvx tasty-agent setup

This will prompt you for your TastyTrade username, password, and account ID (optional if you only have one account).

Option 2: Environment Variables

Alternatively, you can set the following environment variables:

  • TASTYTRADE_USERNAME: Your TastyTrade username
  • TASTYTRADE_PASSWORD: Your TastyTrade password
  • TASTYTRADE_ACCOUNT_ID: Your TastyTrade account number (optional if you only have one account)

Note: If credentials are found in both the keyring and environment variables, the keyring values will take precedence.

Important Notes

  • Scheduled trades will only execute while Claude Desktop is running. When Claude Desktop is closed, the server shuts down and trades are not executed.
  • For security reasons, always verify trade details before execution, especially when using the schedule_trade tool.

Troubleshooting

If you encounter issues with the TastyTrade Portfolio Manager, you can use the MCP inspector for debugging:

npx @modelcontextprotocol/inspector uvx tasty-agent

Log files can be found at:

  • macOS: ~/Library/Logs/Claude/mcp*.log
  • Windows: %APPDATA%\Claude\logs\mcp*.log

Related MCPs

Investor Agent
Finance & FintechPython

Financial analysis and investment insights for LLMs

Bankless Onchain
Finance & FintechTypeScript

Access and interact with blockchain data through the Bankless API

EVM Blockchain Interaction
Finance & FintechTypeScript

Interact with 30+ EVM-compatible blockchain networks

About Model Context Protocol

Model Context Protocol (MCP) allows AI models to access external tools and services, extending their capabilities beyond their training data.

Generate Cursor Documentation

Save time on coding by generating custom documentation and prompts for Cursor IDE.