tastytrade-research-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TASTYTRADE_CLIENT_ID | Yes | tastytrade OAuth client ID | |
| TASTYTRADE_CLIENT_SECRET | Yes | tastytrade OAuth client secret | |
| TASTYTRADE_REFRESH_TOKEN | Yes | tastytrade OAuth refresh token |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tastytrade_get_backtest_available_datesA | List tastytrade Backtester symbols and their available historical date ranges. Use this before regression tests to verify SPY, XSP, SPX, or other symbol coverage. |
| tastytrade_list_backtestsA | List backtests submitted for the authenticated tastytrade API grant. |
| tastytrade_create_backtestA | Create a tastytrade historical options backtest. This is research-only and does not place brokerage orders. |
| tastytrade_get_backtestA | Get a tastytrade backtest by ID, including its current status and results when completed. |
| tastytrade_get_backtest_logsC | Get tastytrade Backtester execution logs for a backtest ID. |
| tastytrade_cancel_backtestA | Cancel a running research backtest. This affects only the Backtester job and never a brokerage order. |
| tastytrade_simulate_tradeA | Simulate a single historical option trade with tastytrade Backtester and return its historical path/results. Research-only; no brokerage order is placed. |
| tastytrade_price_option_packageC | Price a 2-4 leg option package with explicit native-package, synthetic-natural, and midpoint-reference provenance using exact decimal arithmetic. |
| tastytrade_prepare_spx_spreadB | Normalize an SPX debit vertical, credit vertical, iron condor, or double diagonal into deterministic Backtester and exact-leg simulation requests without submitting it. |
| tastytrade_simulate_spx_spreadC | Run exact-leg historical simulation for a normalized SPX defined-risk spread and return a stable regression result contract. |
| tastytrade_create_spx_spread_backtestA | Create an aggregate SPX spread Backtester job when the structure can be represented faithfully enough by relative leg selectors. Double diagonals remain exact-simulation only. |
| tastytrade_verify_historical_fillB | Verify whether a frozen paper-order limit was touched during a forward historical interval. Returns separate post-session evidence and never rewrites the live paper event. |
| tastytrade_get_historical_candlesA | Retrieve normalized historical OHLCV candles from tastytrade DXLink for an exact UTC and session window, with source timestamps and explicit gap warnings. No resampling is performed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 13 tools
Most tools are clearly distinct by resource and action, but the backtest/simulation cluster (create_backtest, simulate_trade, simulate_spx_spread, create_spx_spread_backtest) risks confusion despite clarifying descriptions. The price/prepare/simulate spread pipeline is well-separated with explicit roles.
All tools follow a consistent tastytrade_ prefix with snake_case verb_noun naming (list_backtests, create_backtest, get_backtest_logs, cancel_backtest). Verbs and objects are uniform and predictable across the entire set.
13 tools is well within the ideal 3-15 range for a research-focused server. Each tool contributes to distinct workflows such as backtest management, option pricing, spread simulation, and historical data access without redundancy.
The core research workflow is well covered: backtest lifecycle (list, create, get, cancel, logs), historical simulation, option pricing, spread normalization, and candle retrieval. Minor gaps exist such as lack of a delete-backtest or batch operation, but no critical dead ends are apparent.