Deptho MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Deptho checks crypto perpetual backtests at tick level, on the user's machine. Use replay_orders to estimate what a backtest's market orders would have paid against the trades that followed them (Binance archive aggTrades or Tardis.dev trades files), and tearsheet to attribute returns to fees, funding and slippage. Fills are modeled from trade prints: no order book depth or queue position. All paths are local files.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| replay_ordersA | Replay a backtest's market orders against the trades that followed them. orders_csv: CSV with columns time (ISO or epoch), side (+1/-1 or buy/sell), qty (base units). trades_file: Binance archive aggTrades file (.zip or .csv) or Tardis.dev trades file (.csv or .csv.gz) covering the orders' period. Writes one row per filled order (side, qty, price, ref_price, slippage_bps) to fills_csv (default: next to the orders, .fills.csv) and returns a summary. Slippage is in bps against the last trade before each order; positive = cost. |
| tearsheetA | Write Deptho's HTML tearsheet for a strategy and return its path and headline numbers. bars_csv: CSV with columns time, price (mark/close) and position (exposure as a fraction of equity, 1.0 = 1x long, decided at each bar's close; it earns from the next bar). funding_csv (optional): time and funding_rate (positive = longs pay). fee_bps and slippage_bps: per unit of turnover; use the slippage measured with replay_orders rather than a guess. Writes one self-contained HTML file (default: next to bars_csv, .report.html). |
| pro_statusA | Whether Deptho Pro is installed and licensed here. pro_sync and pro_replay need it. |
| pro_syncA | (Deptho Pro) Download Binance USD-M daily trade files from Binance's public archive for start..end (YYYY-MM-DD, inclusive) and append them to one local memory-mapped dataset, "-aggTrades". Days already on disk aren't downloaded again. Returns the dataset name and size. |
| pro_replayA | (Deptho Pro) Replay an orders CSV (time, side, qty) against a dataset made by pro_sync (the name it returned, e.g. "BTCUSDT-aggTrades"), straight off the memory-mapped columns. Same output as replay_orders. |
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 5 tools
replay_orders and pro_replay have the same output and both replay an orders CSV, differing mainly by data source and Pro licensing. The distinction is explained, but an agent must reason about prerequisites to choose correctly. The remaining tools (tearsheet, pro_status, pro_sync) are clearly distinct.
Most names use a readable verb_noun or prefixed form (replay_orders, pro_status, pro_sync, pro_replay), with a consistent pro_ prefix for licensed tools. The noun-only tearsheet is a minor deviation but remains clear as a domain term.
Five tools is well-scoped for a backtest replay and reporting server. Each tool has a clear role: replay, reporting, and Pro dataset management.
The surface covers the core workflow: syncing trade data, replaying orders, and generating a tearsheet with headline metrics. Minor gaps exist around inspecting intermediate results or non-Pro dataset management, but agents can work around them.