trade-analytics-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DATABENTO_API_KEY | Yes | Your Databento API key (required). Get one at databento.com. | |
| TRADE_ANALYTICS_API_KEY | No | Your trade-analytics API key (required for render/analyze tools). Get one at trade-analytics.o-gw.com/dashboard. | |
| TRADE_ANALYTICS_API_URL | No | Base URL for the trade-analytics API. Defaults to hosted API. | https://trade-analytics.o-gw.com |
| TRADE_ANALYTICS_OUTPUT_DIR | No | Directory where render saves images. Defaults to current working directory. | . |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| resolve_symbolA | Resolve a symbol the user mentioned (e.g. 'MNQ', 'micro nasdaq', 'MNQU6') to its precise Databento notation + trading metadata: root, continuous symbol, dataset, point value, tick size, and best-effort front-month. Runs locally under your Databento key. Free. |
| get_price_contextA | Return OHLCV candles + trade markers as JSON for a symbol/window, fetched locally under your Databento key. Free. Pass fills via |
| renderA | Render a candlestick chart image of a trade (PAID — needs TRADE_ANALYTICS_API_KEY). Fetches your data locally under your Databento key, sends only the numeric slice to the API, and returns the PNG (viewable) AND saves it to a file so you can add it to a journal — the saved path is in the text result. Use |
| analyzeA | Analyze trades (PAID — needs TRADE_ANALYTICS_API_KEY): per-trade MAE/MFE, R-multiple, went-green-first, capture efficiency, USD P&L (with point_value), plus an aggregate summary. Fetches the candles spanning your trades locally, sends only the numeric slice to the API. Pass |
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 4 tools
Each tool has a clearly distinct purpose: symbol resolution, data fetching, chart rendering, and trade analysis. No overlap or ambiguity.
Two tools use verb_noun pattern (resolve_symbol, get_price_context), while two are single verbs (render, analyze). Inconsistent naming convention, though each name is descriptive enough.
4 tools is slightly below average but appropriate for a focused trade analytics server. Each tool covers a core function without being too thin.
Covers the main workflow: symbol resolution, data retrieval, visualization, and analysis. Minor gaps like bulk data or risk management are not core, so overall good coverage.