agi-scorecard MCP server
com.agiscorecard/agi-scorecardagiscorecard.comstreamable-httpv1.0.0Scanned
8 graded AGI-2027 predictions, the 0-100 Thesis Tracker, and a public market-call ledger. Free.
8 tools: 8 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 1
- No findings
Sign-in required, no OAuth metadata. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the agi-scorecard MCP server can do
The agi-scorecard MCP server is published by agiscorecard.com, a domain the MCP Registry verified. It has 8 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool brings in text other people can write (get_claim_ledger); 1 tool can send data out of your system (get_claim_ledger).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 12, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
8 tools
Only reads 8Show 8 read-only tools
get_agi_consensusThe 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% d…No findings
Why it is in this group
- The name "get_agi_consensus" says "get": a word for reading.
Description, as the server wrote it 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
get_claim_ledgerRead 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.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_claim_ledger" says "get": a word for reading.
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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
get_invest_positionsThe 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 fi…No findings
Why it is in this group
- The name "get_invest_positions" says "get": a word for reading.
Description, as the server wrote it 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.
get_portfolio_returnsRead the public twelve-stock model portfolio versus SPY (S&P 500 ETF proxy), QQQ and TQQQ.No findings
Why it is in this group
- The name "get_portfolio_returns" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_sunwatch_track_recordThe SunWatch editorial market-call ledger (invest.agiscorecard.com), outcome labels and evidence audit.No findings
Why it is in this group
- The name "get_sunwatch_track_record" says "get": a word for reading.
Description, as the server wrote it 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.
get_thesis_trackerThe 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.No findings
Why it is in this group
- The name "get_thesis_tracker" says "get": a word for reading.
Description, as the server wrote it 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.
get_verdictsAll 8 graded Situational Awareness predictions with current verdict, evidence summary and primary sources, plus how independent public graders scored the same predictions (verbatim…No findings
Why it is in this group
- The name "get_verdicts" says "get": a word for reading.
Description, as the server wrote it 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.
search_siteSearch every page and tool on agiscorecard.com and its invest/compass sub-sites (English and Chinese).No findings
Why it is in this group
- The name "search_site" says "search": a word for reading.
Description, as the server wrote it Search every page and tool on agiscorecard.com and its invest/compass sub-sites (English and Chinese). Returns titles, descriptions and URLs.
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:33 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 429
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 429.
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 200 to 429
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 429; tools/list served without credentials: yes -> no; Protocol version: 2025-06-18 -> none.View diff
- HTTP status of an anonymous initialize: 200 to 429
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agi-scorecard https://agiscorecard.com/mcpclaude mcp add --transport http agi-scorecard https://agiscorecard.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agi-scorecard__get_portfolio_returns",
"mcp__agi-scorecard__get_thesis_tracker",
"mcp__agi-scorecard__get_verdicts",
"mcp__agi-scorecard__get_sunwatch_track_record",
"mcp__agi-scorecard__get_invest_positions",
"mcp__agi-scorecard__get_agi_consensus",
"mcp__agi-scorecard__search_site"
],
"ask": [
"mcp__agi-scorecard__get_claim_ledger"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agi-scorecard. Review it before you use it.
Capability tags behind 1 rule
- mcp__agi-scorecard__get_claim_ledger untrusted-input, outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.agiscorecard/agi-scorecard/verify?hash=09235ed672f113452addef1380e6d780a578deea2902733470d812d570530564" | jq -e '.changed == false'Pinned hash 09235ed672f1, from Nov 12, 2026, 13:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.agiscorecard/agi-scorecard/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.agiscorecard/agi-scorecard)Source: MCP Registry. Synced Oct 21, 2026, 17:48 UTC.
agi-scorecard MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the agi-scorecard MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the agi-scorecard MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the agi-scorecard MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the agi-scorecard MCP server have?
- 8 tools: 8 read. get_portfolio_returns, get_thesis_tracker, get_verdicts, get_sunwatch_track_record, get_claim_ledger, get_invest_positions, get_agi_consensus and search_site.
Does the agi-scorecard MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the agi-scorecard MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): get_claim_ledger.
Has the agi-scorecard MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.