Skip to main content
Glama
haiyunsky

HPSILab - Quant Finance MCP Server for Stock Analysis and Options Analytics

by haiyunsky
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

get_ai_prediction

Read-onlyIdempotent

Predict a stock’s next-session direction using an AI ensemble; get up probability, per-model votes, confidence, and regime context to support trading and IV comparison.

Instructions

Get an AI/ML directional prediction for a stock's next-session move.

Use this tool when:

  • You want a data-driven probability estimate for the next trading day's direction (up vs. down).

  • You need the individual model votes (ensemble breakdown) to assess consensus strength.

  • You want to compare model confidence against current IV pricing.

The prediction engine uses an ensemble of gradient-boosted trees, an LSTM, and a VQC (quantum-classical hybrid) model. Features include VIX, relative strength, Treasury rates, and options flow signals.

Returns

dict with keys: symbol : str — normalized ticker prediction : str — "Up" | "Down" | "Neutral" up_probability : float — 0.0–1.0 probability of upward close confidence : float — 0.0–1.0 ensemble agreement score model_votes : dict — per-model predictions and probabilities regime : str — "Bull" | "Bear" | "Chop" market regime signal_strength : str — "Strong" | "Moderate" | "Weak"

Input Schema

NameRequiredDescriptionDefault
symbolYesExchange ticker in uppercase, e.g. 'NVDA', 'META', 'QQQ'. Do NOT pass company names — use official tickers only. Per-ticker model accuracy varies; META and QQQ have shown above-baseline hit rates in backtests.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.11.1
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "get_ai_predictionDictOutput",
+  "type": "object"
+}
  2. Changed3 schema fields changedv0.3.1
    • addedInput schema / properties / symbol / description
      Added value: +"Exchange ticker in uppercase, e.g. 'NVDA', 'META', 'QQQ'. Do NOT pass company names — use official tickers only. Per-ticker model accuracy varies; META and QQQ have shown above-baseline hit rates in backtests."
    • addedInput schema / properties / symbol / examples
      Added value: +[
+  "NVDA",
+  "META",
+  "QQQ"
+]
    • addedInput schema / properties / symbol / pattern
      Added value: +"^[A-Z][A-Z0-9.-]{0,15}$"
  3. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare the tool as read-only, idempotent, open-world, and non-destructive. Beyond that, the description discloses the ensemble composition (gradient-boosted trees, LSTM, VQC), feature inputs, and returned fields like confidence and regime, which is useful behavioral context. It does not cover latency, data freshness, or failure modes.

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?

The description is front-loaded with a clear purpose sentence, followed by well-structured use-case bullets and a labeled returns section. It is somewhat verbose in listing return keys even though an output schema exists, but the content remains relevant and easy to scan.

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?

For a one-parameter, read-only prediction tool with annotations and an output schema, the description covers purpose, use cases, model basis, and output semantics thoroughly enough to invoke it correctly. It lacks explicit sibling routing and operational caveats like data freshness or limitations, which keeps it from a 5.

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

Parameters3/5

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

There is only one parameter and the schema description coverage is 100%; the schema already documents the ticker format, pattern, examples, and per-ticker accuracy caveats. The description adds no parameter-specific guidance beyond implying a stock ticker, so the high-coverage baseline of 3 is appropriate.

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

Purpose4/5

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

The first sentence states a specific verb and resource: get an AI/ML directional prediction for a stock's next-session move. The use-case bullets further scope it to next-day direction, ensemble votes, and IV comparison, which distinguishes it functionally from broader siblings like analyze_stock. It does not explicitly name sibling tools, so it falls short of a 5.

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

Usage Guidelines4/5

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

The description provides an explicit 'Use this tool when' section with three concrete conditions: wanting a probability estimate, needing ensemble votes, or comparing confidence to IV pricing. It gives clear use context but does not state when not to use it or explicitly name alternatives such as get_iv_radar or get_monte_carlo.

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

Deploy Server

Other Tools