Skip to main content
Glama

TradingMCP

by io.github.atilaahmettaner
OverviewDiscussionsAdmin

Smart Money Analysis

smart_money_analysis
Read-only

Banker/hot-money proxy read for one symbol from price+volume history.

Three independent families, computed from Yahoo Finance OHLCV:
  - mcdx_style: RSI-horizon decomposition (banker RSI50 / hot-money RSI40
    / retail RSI14, each scaled 0-20) — sustained slow-horizon strength
    that fast horizons can't fake reads as institutional accumulation.
  - banker_fund_oscillator: EMA(13)-smoothed 34-bar stochastic of the
    weighted typical price, 0-100, with BANKER_ENTRY/EXIT states.
  - volume_flow_composite: CMF(20) + MFI(14) + OBV trend + up/down volume
    balance → 0-100 accumulation score.
Plus a consensus vote across the three.

These are documented, reproducible formula variants inspired by the
public "banker fund" indicator family — NOT actual institutional-flow
data, and not copies of any closed-source script.

Args:
    symbol: Bare ticker — EGX: "COMI", "TMGH"; US: "AAPL"; crypto pairs
        work via Yahoo notation ("BTC-USD").
    exchange: EGX (maps to Yahoo .CA), BIST (.IS), TADAWUL (.SR); anything
        else passes the symbol to Yahoo unchanged.
    period: 1mo | 3mo | 6mo | 1y | 2y (default 6mo)
    interval: 1d (default) or 1h

Input Schema

NameRequiredDescriptionDefault
periodNo6mo
symbolYes
exchangeNoEGX
intervalNo1d

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds genuinely valuable behavioral context beyond them: the data source (Yahoo Finance OHLCV) and the important caveat that these are documented formula variants, NOT actual institutional-flow data — preventing misuse/misinterpretation. It still omits rate limits or cost, so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then structured into labeled families and an Args block, so it is scannable. Some formula detail (RSI50/RSI40/RSI14 scaling, EMA(13)-smoothed 34-bar stochastic) is more granular than selection strictly needs, but it aids output interpretation rather than adding pure waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should convey return shape — and it does, stating each family's range (0-20, 0-100) and the consensus vote. Combined with the source and proxy caveat, an agent has enough to call and interpret it; only concrete field names/response structure are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden and does so well: it documents all four parameters, gives bare-ticker examples, explains exchange-to-Yahoo suffix mapping (.CA/.IS/.SR, else pass-through), and lists period/interval values with defaults. This fully compensates for the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource ('Banker/hot-money proxy read for one symbol from price+volume history') and names the exact three indicator families computed. The 'for one symbol' scoping implicitly distinguishes it from scanner siblings like egx_smart_money_scanner, so an agent can route correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by describing what each family measures and how to interpret accumulation, but there is no explicit when-to-use, when-not-to-use, or named-alternative guidance. The agent can infer it's a single-symbol diagnostic but gets no routing rules against the many sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All TradingMCP toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources