# Æfact — Korean fact desk for AI agents (remote · aefact.site)

Verified Korean facts: law changes by date, Bank of Korea figures, fact-check requests.

- Trust score: 77/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `aefact.site`: 77/100 (this document), [markdown](https://verifymcp.io/servers/site-aefact-aefact/aefact.md), [page](https://verifymcp.io/servers/site-aefact-aefact/aefact)

## Channel facts

- Endpoint: `https://aefact.site/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.1`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 62/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2586 tokens (~184/item across 14 items; 14 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 91/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 73% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Æfact — Korean fact desk for AI agents MCP server?

Æfact — Korean fact desk for AI agents is a hosted endpoint at https://aefact.site/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http site-aefact-aefact 'https://aefact.site/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "site-aefact-aefact": {
      "url": "https://aefact.site/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "site-aefact-aefact": {
      "type": "http",
      "url": "https://aefact.site/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.site-aefact-aefact]
url = "https://aefact.site/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "site-aefact-aefact": {
      "type": "remote",
      "url": "https://aefact.site/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add site-aefact-aefact --url 'https://aefact.site/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  site-aefact-aefact:
    url: "https://aefact.site/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "site-aefact-aefact": {
      "Transport": "http",
      "Url": "https://aefact.site/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add site-aefact-aefact -t streamable-http -u 'https://aefact.site/mcp'
```

### Other

```json
{
  "mcpServers": {
    "site-aefact-aefact": {
      "type": "http",
      "url": "https://aefact.site/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 76, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 2242 → 2586
- [functional] Server version: 0.5.0 → 0.6.0
- [functional] New tool “fact_check”

### 2026-10-31 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 72, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Schema quality: 155 → 172
- [functional] Server version: 0.4.0 → 0.5.0
- [functional] New tool “trending”

### 2026-10-21 (score 71, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (14)

### `what_changes` (~258 tokens)

바뀌는 제도

언제부터 무엇이 바뀌나. 기간(from~to)·분야·검색어로 시행되는(또는 막 시행된) 한국 법령 변경을 찾습니다. 결과마다 시행일, 법령명, 바뀌는 문구, 개정이유 첫 문장(법제처 원문 그대로)이 있습니다. 자세한 원문은 get_change. EN: What Korean laws/regulations change between dates (effective dates from the Ministry of Government Legislation), with verbatim reasons and changed wording.

Input parameters:

- `from` (string): 시작일 YYYY-MM-DD (기본: 오늘)
- `limit` (integer)
- `query` (string): 예: 전세, 근로자, 건강보험, 육아휴직
- `to` (string): 끝일 YYYY-MM-DD (기본: 30일 뒤)
- `topic` (string): 분야(일·노동, 복지·건강, 세금·금융·경제, 주거·교통, 교육·가족, 안전·행정·사법, 환경·에너지, 농어업, 문화·관광, 과학·디지털, 국방·외교·보훈)

### `trending` (~300 tokens)

실시간 모음

지금 나온 한국 정부·공공 소식을 한 목록으로: 정책브리핑 보도자료·정책뉴스, 국민참여입법센터 입법예고(조회수·의견수), 법제처 시행 법령, Æfact 검산. 같은 소식은 묶어 출처 수를 세고, 주목도(출처 안 상대 순위·여러 출처·AI 독자 수·시간 감쇠, 규칙 계산)·최신·AI가 많이 읽은 순·의견순으로 늘어놓습니다. 제목·원문 링크만 있고 본문은 없습니다. 판정이 아니며, 판정은 check_url 에 있습니다. EN: Trending Korean government/public announcements (press releases, policy news, legislative notices with views/opinions, laws taking effect), deduplicated across sources and ranked by a transparent rule-based score.

Input parameters:

- `limit` (integer)
- `query` (string): 제목·기관에 들어간 낱말(예: 전세, 반도체)
- `sort` (string): hot 주목도순 · new 최신순 · ai AI가 많이 읽은 순 · talk 입법예고 의견·조회순
- `source` (string): 출처 하나만(보도자료·정책뉴스·입법예고·시행 법령·Æfact 검산)
- `window` (string): 기간

### `get_change` (~74 tokens)

변경 카드 원문

what_changes 결과의 id(chg-…)로 변경 카드 하나를 받습니다: 개정이유 전문, 바뀌는 문구 전체, 시행일 조항, 이날 시행되는 조문, 인용 한 줄(cite). EN: Full verbatim change card by id.

Input parameters:

- `id` (string, required)

### `fact_check` (~259 tokens)

AI 팩트체크

글(답변 초안·기사·보고서, 4000자까지)을 통째로 넘기면 팩트체크가 필요한 문장을 골라 대신 확인합니다. 법령 시행일·한국은행 기준금리·월별 소비자물가 상승률은 원자료와 대조하고, 문장 안 증감률·비율·합계는 다시 계산합니다. 문장마다 status(확인함·사람 확인 필요·원자료 미연결·확인 대상 아님·다루지 않음)와 계산·근거 주소가 오고, attention 에 손봐야 할 문장 번호가 옵니다. 판정은 규칙·계산이며 모델을 쓰지 않습니다. 글은 저장·공개하지 않습니다. EN: Hand over a whole Korean text; Æfact picks the sentences that need fact-checking and verifies them against primary data (law effective dates, BOK base rate, monthly CPI) or by recomputing in-sentence arithmetic. Returns per-sentence status, calculations and evidence URLs. Rule-based, no LLM. Text is not stored.

Input parameters:

- `text` (string, required): 확인할 글. 문장이 여러 개여도 됩니다.

### `request_check` (~279 tokens)

확인 요청

한국에 관한 사실 문장 하나의 확인을 Æfact에 요청합니다. 법령 시행일·한국은행 기준금리·월별 소비자물가 상승률·문장 안 증감률·비율·합계는 바로 원자료로 판정해 공개 결과 주소(url)와 인용 한 줄(cite)을 돌려줍니다. 그 밖의 문장은 접수(status=queued)되어 수요로 집계됩니다. 결과는 공개됩니다(개인정보·정치·수사·재판·의료·연예 사생활 문장은 받지 않음). 같은 문장은 같은 결과를 돌려줍니다. EN: Submit a Korean factual claim for verification. Decidable claims (law effective dates, BOK base rate, monthly CPI, in-sentence arithmetic) are judged immediately against primary data and published at a public URL.

Input parameters:

- `claim` (string, required): 확인할 문장 하나(원문 그대로). 예: 근로기준법 개정안은 12월 8일부터 시행된다 / 9월 소비자물가 상승률은 2.9%다
- `context` (string): 선택: 맥락(누가·언제 한 말인지 등)
- `source_url` (string): 선택: 문장이 나온 주소

### `get_request` (~48 tokens)

확인 요청 결과

request_check 가 돌려준 id(rq_…)로 요청 상태와 결과를 다시 봅니다. EN: Get a verification request's status/result by id.

Input parameters:

- `id` (string, required)

### `lookup` (~151 tokens)

한 번에 찾기

질문에 나온 대상(법령·기관)과 지금 참인 사실을 한 번에 찾습니다. 처음엔 이 도구를 쓰세요. 띄어쓰기·가운뎃점은 무시합니다. 사실마다 freshness(낡음 여부)와 cite(답변에 붙일 인용 한 줄)가 있습니다. EN: One-call lookup of Korean entities (laws, agencies) and current verified facts (economic indicators, law effective dates). Each fact has freshness and a ready-to-paste citation.

Input parameters:

- `limit` (integer)
- `query` (string, required): 예: 기준금리, 원달러 환율, 개인정보보호법, 국토교통부

### `search_entities` (~124 tokens)

대상 검색

법령·기관 같은 대상을 이름으로 찾습니다. 현행 법령 전체와 소관부처, 한국은행이 있습니다. 결과의 id로 get_entity를 부르면 그 대상의 현재 사실과 연결(상위법·하위법·소관부처)을 받습니다.

Input parameters:

- `limit` (integer)
- `query` (string): 대상 이름이나 약칭. 공백으로 나눈 낱말이 모두 들어간 것만 돌려줍니다.
- `type` (string): law(법령) 또는 org(기관)

### `get_entity` (~132 tokens)

대상 하나 조회

대상 하나의 속성(근거 출처 포함), 현재 사실, 연결된 대상을 줍니다. 법령이면 상위법·하위법(시행령·시행규칙)·소관부처, 기관이면 소관 법령 목록입니다. 연결은 원자료(법제처 법령 체계도·법령 목록)에서 확인된 것만 있습니다.

Input parameters:

- `id` (string, required): 대상 id. 예: law-011357, org-1790365, org-bok
- `relation_limit` (integer): 돌려줄 연결 수 상한

### `search_facts` (~158 tokens)

현재 사실 검색

지금 참인 사실(상태)을 찾습니다. 기준금리·환율·소비자물가지수 같은 경제지표, 시행 예정 법령, 현행 법령 버전(법령마다 1건)이 있습니다. 결과마다 현재 값, 언제부터 참인지(valid_from), 문장, id가 있습니다. 자세한 이력은 get_fact로 보세요.

Input parameters:

- `category` (string): economy(경제지표), law(제도·법령), companies(기업·공시)
- `limit` (integer)
- `query` (string): 찾을 말. 공백으로 나눈 낱말이 모두 들어간 사실만 돌려줍니다. 비우면 전체.

### `get_fact` (~127 tokens)

사실 하나 조회

사실 하나의 현재 버전과 이력을 줍니다. as_of(YYYY-MM-DD)를 주면 그날 참이던 버전을 줍니다. 버전마다 valid_from, valid_until, superseded_by, 근거(원자료 값)가 있습니다.

Input parameters:

- `as_of` (string): 이 날짜에 참이던 버전을 원할 때(YYYY-MM-DD)
- `history_limit` (integer): 함께 돌려줄 과거 버전 수
- `id` (string, required): 사실 id. 예: kr-bok-base-rate. search_facts 결과의 id

### `search_articles` (~71 tokens)

기사 검색

기사를 찾습니다. 기사는 사실의 값이 바뀐 시점의 기록입니다. 지금 값이 필요하면 search_facts를 쓰세요.

Input parameters:

- `category` (string)
- `limit` (integer)
- `query` (string): 찾을 말. 비우면 최신순 전체.

### `get_article` (~65 tokens)

기사 전문 조회

기사 전문과 문장별 판정을 줍니다. 각 판정의 fact_status.is_current가 false면 그 문장은 이후 바뀐 사실이므로 현재 사실로 인용하지 마세요.

Input parameters:

- `slug` (string, required): 기사 slug. search_articles 결과의 slug

### `list_categories` (~35 tokens)

분야와 판정 기준

다루는 분야, 분야별 건수, 다루지 않는 분야, 판정 어휘의 뜻을 줍니다.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/site-aefact-aefact/aefact#diagnostics

## Score history

- 2026-11-04: 77
- 2026-11-03: 77
- 2026-11-02: 76
- 2026-11-01: 76
- 2026-10-31: 76
- 2026-10-30: 75
- 2026-10-29: 75
- 2026-10-28: 74
- 2026-10-27: 74
- 2026-10-26: 73
- 2026-10-25: 73
- 2026-10-24: 72
- 2026-10-23: 72
- 2026-10-22: 72
- 2026-10-21: 71
- 2026-10-20: 71

## Common questions

### What is the Æfact — Korean fact desk for AI agents MCP server?

Æfact — Korean fact desk for AI agents is an MCP server listed in the public MCP registry as site.aefact/aefact. Verified Korean facts: law changes by date, Bank of Korea figures, fact-check requests. This page covers its hosted endpoint (https://aefact.site/mcp).

### Is the Æfact — Korean fact desk for AI agents MCP server safe to use?

Æfact — Korean fact desk for AI agents scores 77 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Æfact — Korean fact desk for AI agents MCP server expose?

Æfact — Korean fact desk for AI agents exposes 14 tools: what_changes, trending, get_change, fact_check, request_check, and 9 more. Their descriptions and schemas cost roughly 2,081 tokens of context every time the server is loaded.

### Does the Æfact — Korean fact desk for AI agents MCP server require authentication?

No. We connected to Æfact — Korean fact desk for AI agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Æfact — Korean fact desk for AI agents MCP server still maintained?

Æfact — Korean fact desk for AI agents is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://aefact.site/mcp
- Repository: https://github.com/cizion/aefact-mcp
- Website: https://aefact.site/
- Changelog RSS feed: https://verifymcp.io/servers/site-aefact-aefact/aefact.xml
- Changelog JSON feed: https://verifymcp.io/servers/site-aefact-aefact/aefact.json
- HTML version of this page: https://verifymcp.io/servers/site-aefact-aefact/aefact