quant-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.
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
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_symbolsA | Lists the instruments this server can analyse, and where their data comes from. |
| get_ohlcA | Returns recent candles for a symbol. Long ranges are truncated to the most recent rows; the response states the total available. |
| indicatorA | Computes SMA, EMA, RSI, ATR or Bollinger bands. Values are aligned with the candles and null before the indicator has enough history, so a caller cannot silently shift the series. |
| backtestA | Runs a strategy over the history and returns metrics, the trade list and the equity curve. Signals fill at the next bar's open, costs are charged both sides, and a bar touching both stop and target counts as a stop. The assumptions come back with the result. |
| position_sizeA | Turns account equity, risk tolerance and a stop distance into a position size. Refuses inputs that would risk more than the account or imply a zero stop. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| analyse_symbol | A structured walk through price, trend, momentum and volatility for one instrument. |
| review_backtest | Runs a strategy and interrogates the result instead of celebrating it. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| symbols | The instruments this server can analyse. |
| methodology | The execution model every backtest result assumes. |
TDQS
Scored across 5 tools
Each tool covers a distinct aspect of the quant workflow: symbol discovery, OHLC data, indicator calculation, backtesting, and position sizing. There is no meaningful overlap or ambiguity between them.
Naming is readable but not uniform: list_symbols and get_ohlc follow a verb_noun pattern, while backtest, indicator, and position_size are single verbs or noun phrases. The inconsistency is noticeable but not confusing.
Five tools is well-scoped for a quantitative analysis server. Each tool serves a necessary step in the analysis workflow without redundancy or bloat.
The set covers the core workflow: discover symbols, retrieve data, compute indicators, run backtests, and size positions. Minor gaps exist around strategy persistence or more granular risk controls, but they do not create dead ends for the stated purpose.