Alphalabs Intelligence

io.github.Pak209Published by GitHub account Pak209v1.0.0Updated Oct 24, 2026

Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.

VerifiedStreamable HTTPWeb executableFinance

Overview

AI-generated overview

Lets an assistant score trade ideas with the AlphaLabs engine and read aggregated calibration, outcome, and feature-attribution statistics.

What you can do
Exposes tools over the AlphaLabs trading-signal engine: list products and prices, score the user's own trade idea through a deterministic engine and return an evaluation ID, explain a prior evaluation's sub-signals and weights, and retrieve aggregated telemetry on pipeline calibration, recorded outcomes, and feature attribution.
When to use it
Use it when you want a consistent scoring rubric applied to your own trade ideas, or want to inspect how a signal engine has been calibrated and how its past decisions performed. It is not for live quotes, order placement, or account data.
Requirements
Remote endpoint; no local package. An API key is supplied in the Authorization header; free beta keys are requested by email.
Before you install
Requires an API key in the Authorization header, so keep it private. Results are aggregated engine telemetry and scores only; no positions, orders, or account data exist on this surface, and price/volume confirmation is not evaluated. Treat output as informational, not investment advice.

Installation

In SourceWeft

  1. Open Alphalabs Intelligence in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Pak209%2Falphalabs-intelligence/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "alphalabs-intelligence": {
      "type": "http",
      "url": "https://api.pak-labs.com/mcp"
    }
  }
}

Tools

6

alphalabs_get_catalog

Free: list AlphaLabs Intelligence products, prices, and auth model.

Takes no parameters.

alphalabs_calibration_report

Live paper-trading pipeline calibration telemetry: stage funnel, gate failures, near-misses. Derived analytics only — no positions, orders, or account data exist on this surface.

Takes no parameters.

alphalabs_evaluate_signal

Score YOUR trade idea through the live AlphaLabs deterministic engine: composite score, tier, per-component sub-signals, floors. Price/volume confirmation is not evaluated (no vendor market data). Returns an evaluation_id for alphalabs_explain_decision.

Parametersbiasrequiredthesistickerrequiredcatalystconfidencecatalyst_typecatalyst_score

alphalabs_outcome_report

Recorded outcomes of the live pipeline's own decisions: hit rates, score-band tables, accepted-vs-rejected edge, gate near-miss regret. Aggregated engine telemetry — percent moves and counts only.

Takes no parameters.

alphalabs_feature_attribution

Which engine inputs actually predict outcomes, measured on recorded live results: Spearman rankings, median-split deltas, dead inputs.

Takes no parameters.

alphalabs_explain_decision

Glass-box breakdown of a prior evaluation by evaluation_id: every sub-signal, weight, floor, and the composite reasoning.

Parametersevaluation_idrequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

83% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.