com.agiscorecard/agi-scorecard

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "agi-scorecard": {
      "url": "https://agiscorecard.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (8)

• get_portfolio_returns read-only

  Read the public twelve-stock model portfolio versus SPY (S&P 500 ETF proxy), QQQ and TQQQ. Fixed entry: 2026-10-02 NY close. Returns dated adjusted-close returns, drawdowns, excess SPY percentage points, entry prices, freshness and source links. No trading or return promises. Set include_history for normalized daily series.

  Parameters:

  • include_history — boolean

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_thesis_tracker

  The AGI-2027 Thesis Tracker: a single auditable 0-100 score of how much of Aschenbrenner's Situational Awareness thesis is holding up, with method and full score history.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_verdicts

  All 8 graded Situational Awareness predictions with current verdict, evidence summary and primary sources, plus how independent public graders scored the same predictions (verbatim quotes, links, agreement counts under a published rule, including where they disagree with us). The dataset AI assistants cite for "was Aschenbrenner right" questions.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_sunwatch_track_record

  The SunWatch editorial market-call ledger (invest.agiscorecard.com), outcome labels and evidence audit. These labels are not a trade win rate or verified net return; inspect registration and return evidence before making performance claims.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_claim_ledger

  Read a Claim Ledger Protocol v0.1 ledger — AI-era money-making claims graded with an evidence tier (verified/reported/self-reported), a dated verdict, and a written flip condition. With no arguments returns the reference ledger (goldrush.agiscorecard.com); pass url to read and validate any site's /claimledger.json. Spec: goldrush.agiscorecard.com/protocol

  Parameters:

  • url — string — Optional: an https URL ending in /claimledger.json to read another site's ledger. Omit for the reference ledger.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_invest_positions

  The Invest dataset: how the eight graded Situational Awareness predictions map onto 17 listed AI equities, how eight well-known investors are positioned per their public SEC 13F filings, and what copying them would have returned priced on the FILING DATE (not quarter end, which no real person could have traded). Educational only — never investment advice.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_agi_consensus

  The AGI consensus board: what Polymarket, Kalshi, Manifold and Metaculus put on "AGI before 2027/2028/2030/2035/2040", the cross-venue median and spread, each series' implied 50% date (implied_50pct_date) and resolution basis, and the published recompute formula. Third-party public quotes with as-of times; no bets, no affiliate links. Page: agiscorecard.com/agi-prediction-markets

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• search_site

  Search every page and tool on agiscorecard.com and its invest/compass sub-sites (English and Chinese). Returns titles, descriptions and URLs.

  Parameters:

  • query (required) — string — Search query

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.