← Registry

AI & Machine Learning

aioq.org

Provides access to AIO scholarly papers and benchmark data on AI governance and societal effects.

1 endpoint17 known toolsFirst detected August 14, 2026Last detected August 15, 2026

ENDPOINT 1

https://aioq.org/mcp

No auth detected

MCP server metadata

Name
aio
Version
1.0.0
Capabilities
tools
Server instructions

AIO — AI Integrity Organization is an international standards body (Swiss association, Geneva) that builds measurement infrastructure for AI integrity. Use get_framework_vocabulary to read the AIO Framework V/E/S vocabulary and the AIO 20002 record grammar — the machine-readable form of the standard. Use get_benchmark_distribution for measured value/evidence/source hierarchies of frontier models, list_papers and get_paper for the research library, search_atlas for the wider AI research literature, and list_standards_packs / get_standards_pack for AIO formalizations of external norms such as the EU AI Act. AIO Tier 0 measurement runs entirely through this server: register_for_certification declares the model, get_eval_items returns the public Gate A item set, start_eval_attempt issues one dual-gate paper, submit_eval scores it, and verify_certification checks any registry id. Tier 0 does not certify and applies no pass threshold — every completed attempt yields a signed SCORE REPORT (id AIO-S0-…) carrying both gate scores, the per-provision breakdown, the measurement conditions, and a descriptive reference band. The registry also holds legacy certificates (AIO-C0-…) from the period when a threshold existed; those are preserved as issued and still verify. Tier 0 is free, but the model version and an accountable operator must be registered, and the report is published to the public registry — confirm with the user before calling the two writing tools (register_for_certification, submit_eval). All AIO data returned here is licensed CC BY 4.0. Attribute as: AIO — AI Integrity Organization, https://aioq.org, CC BY 4.0.

Known tools 17

search_atlas

Search the AIO Atlas — a trimmed proxy over the OpenAlex index of scholarly works on AI, its governance, and its societal effects.

Inferred read-only
list_papers

List every paper published by AIO — id, track, year, bilingual (en/ko) title and abstract, and an absolute PDF URL.

Inferred read-only
get_paper

Fetch one AIO paper by id (e.g.

Inferred read-only
get_benchmark_distribution

Judgment distributions from the AIO 20003 benchmark: per model, the value (L4), evidence (L3), and source (L2) win-rate hierarchies, reliability figures (TRR, PCS), and links to the raw JSON.

Inferred read-only
get_bench_items

Fetch the public forced-choice item set of the agent-submitted benchmark track: 105 items per layer (L4 values, L3 evidence, L2 sources), each a scenario in which two variables lead to opposite conclusions.

Inferred read-only
submit_bench_run

Submit answers to the agent-track item set from get_bench_items.

Inferred read-only
get_framework_vocabulary

The machine-readable AIO Framework vocabulary: 19 value codes, 10 evidence codes, 10 source codes, the context axes (domain, scope, reversibility, time horizon), the AIO 20002 record grammar, and a JSON Schema for one record line.

Inferred read-only
list_standards_packs

List the standards packs — versioned formalizations of external reference norms (e.g.

Inferred read-only
get_standards_pack

Fetch one standards pack by id, including the full per-provision V/E/S mapping.

Inferred read-only
register_for_certification

Register a model for AIO Tier 0 measurement.

Inferred read-only
get_eval_items

Fetch the public item set for a standards pack — the Gate A half of AIO Tier 0.

Inferred read-only
start_eval_attempt

Start one AIO Tier 0 attempt and receive the exam paper: the public Gate A items plus the Gate B items drawn for this attempt from a private, rotating variant pool (3 per mapped provision, expected answers, provenance, and — since methodology v2-draft — the provision label withheld, because identifying which provision a scenario engages is part of the judgment being measured).

Inferred read-only
submit_eval

Submit Tier 0 answers for automatic scoring.

Inferred read-only
verify_certification

Verify an AIO registry record by id.

Inferred read-only
list_rfcs

List the AIO public RFC rounds — the review rounds in which a contested standards-pack or methodology decision is put out for public comment before it is treated as settled.

Inferred read-only
get_rfc

Fetch one public RFC round by id (e.g.

Inferred read-only
submit_rfc_comment

Submit a comment on an open AIO public RFC round.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

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

Codex

~/.codex/config.toml

[mcp_servers.aio]
url = "https://aioq.org/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "aio": {
      "type": "http",
      "url": "https://aioq.org/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: aio
Remote MCP URL: https://aioq.org/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": {
    "aio": {
      "url": "https://aioq.org/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "aio": {
      "type": "http",
      "url": "https://aioq.org/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "aio",
  "transport": "streamable-http",
  "url": "https://aioq.org/mcp"
}
MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for aioq.org was fetched 2026-08-21T10:51:12.004Z.

Trust status Trusted

aioq.org is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.