INDIVIDUAL MCP TOOL

alphalabs_evaluate_signal

Score YOUR trade idea through the live AlphaLabs deterministic engine: composite score, tier, per-component sub-signals, floors.

pak-labs.comnone authenticationAvailability not checked

LIVE ENDPOINT

https://api.pak-labs.com/mcp

No auth detected

Connect to this endpoint to inspect the live schema for alphalabs_evaluate_signal and invoke it with your own arguments.

{}

Potential side effects detected · medium confidence · heuristic, not a guarantee.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.alphalabs-intel]
url = "https://api.pak-labs.com/mcp"
enabled = true

Claude Code

.mcp.json

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

Claude Desktop

Settings → Connectors → Add custom connector

Name: alphalabs-intel
Remote MCP URL: https://api.pak-labs.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "alphalabs-intel": {
      "url": "https://api.pak-labs.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

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

Generic MCP

Client-specific MCP configuration

{
  "name": "alphalabs-intel",
  "transport": "streamable-http",
  "url": "https://api.pak-labs.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

alphalabs_get_catalog — Free: list AlphaLabs Intelligence products, prices, and auth model.
alphalabs_calibration_report — Live paper-trading pipeline calibration telemetry: stage funnel, gate failures, near-misses.
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.
alphalabs_feature_attribution — Which engine inputs actually predict outcomes, measured on recorded live results: Spearman rankings, median-split deltas, dead inputs.
alphalabs_explain_decision — Glass-box breakdown of a prior evaluation by evaluation_id: every sub-signal, weight, floor, and the composite reasoning.