SCRIPTMASTERLABS — Calibration Court

com.scriptmasterlabsPublished by scriptmasterlabs.comv1.0.4Updated Nov 5, 2026

Calibration leaderboard + paid recalibration via x402. Settle-proven 2026-11-02 (SELF-PROOF).

The publisher's own server: SCRIPTMASTERLABS — B20 Truth

VerifiedStreamable HTTPWeb executableFinanceData & AnalyticsAI & ML

Overview

AI-generated overview

Scores decision-model probability forecasts against real outcomes, with a free leaderboard, calibration reports and ledger checks, plus paid recalibration.

What you can do
  • Rank decision models by Brier score on resolved real-world questions
  • Read a single model's calibration report: Brier, ECE, reliability bins with Wilson intervals, overconfidence and drift
  • Recompute the ledger's SHA-256 hash chain and cross-check derived tables
  • Recalibrate a model's raw probabilities against resolved outcomes on the ledger (paid)
  • Fit isotonic calibration on your own labelled probability/outcome pairs and recalibrate given probabilities (paid, stateless)
When to use it
Useful when you want to judge how well a forecasting or decision model is calibrated, compare models on resolved questions, or map raw probabilities to empirically calibrated ones before relying on them.
Requirements
A remote streamable HTTP endpoint; no package, account, API key or environment variable is declared. The paid tools require an x402 payment in one of the listed assets.
Before you install
Two tools are paid through x402 and spend cryptocurrency (USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau), so a wallet and funds are needed. The recalibration tool refuses below 30 samples. The labelled-pairs tool is described as stateless, but the paid calls still send your data to a third-party endpoint.

Installation

In SourceWeft

  1. Open SCRIPTMASTERLABS — Calibration Court 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/com.scriptmasterlabs%2Fcalibration-court/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": {
    "scriptmasterlabs-calibration-court": {
      "type": "http",
      "url": "https://calibration-court.onrender.com/mcp"
    }
  }
}

Tools

5

court_leaderboard

Live ranking of decision models by Brier score on resolved real-world questions. Free. Returns empty lists when nothing has resolved.

Parameterstask_type

court_model_report

Calibration report for one model: Brier, ECE, reliability bins with Wilson intervals, overconfidence, drift. Free.

Parametersmodelrequiredtask_type

court_verify_ledger

Recompute the SHA-256 hash chain and cross-check derived tables. Free.

Takes no parameters.

court_recalibrate

Paid (x402: USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau). Map a model's raw probability to an empirically calibrated one using resolved outcomes on the ledger. Refuses with insufficient_data below 30 samples.

Parametersprobrequiredmodelrequiredtask_type

court_calibrate_labels

Paid (x402: USDC on Base, USDC on Solana, XRP on XRPL, USDC on Arc, or XAH on Xahau). Fit isotonic calibration on YOUR labelled outcomes ({p,y} pairs) and recalibrate the given probabilities. Stateless; nothing is stored.

Parametersprobsrequiredexamplesrequired

Version history

4
  1. v1.0.4LatestNov 5, 2026
  2. v1.0.3Nov 3, 2026
  3. v1.0.1Oct 26, 2026
  4. v1.0.0Oct 24, 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.

Other Scriptmasterlabs integrations