Local Markdown library of the papers an evidence review cites: metadata, abstract and full text
Its author marked it deprecated in the MCP Registry
Korean policy & finance facts with primary-source citations (laws, gov notices) for AI agents
archive.md MCP & Data Hub is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
Korean policy & finance facts with primary-source citations (laws, gov notices) for AI agents
# 1 — add it to Claude Code
claude mcp add --scope user --transport http archive-md-mcp-data-hub https://choiflix.md/mcp
# 2 — ask your agent for something these tools do
# search_facts, search_verified_facts, get_fact and 7 more
archive.md MCP & Data Hub costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http archive-md-mcp-data-hub https://choiflix.md/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
What the model actually sees. Descriptions are diffed on every release — see version history.
한국 금융·부동산·정부지원금·법령 등 1차 공식 출처로 교차검증된 팩트 레코드(F-01~F-44)를 키워드·도메인·상태로 검색합니다. 무인증 요청에는 공개 팩트(active/expired)만 반환되며 internal_read 스코프 API 키가 있을 때만 draft 팩트가 포함됩니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| domain | string | no | — |
| status | string | no | — |
| as_of | string | no | — |
| limit | integer | no | — |
search_facts의 하위 호환 별칭 도구입니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| domain | string | no | — |
| limit | integer | no | — |
영구 팩트 ID(예: F-01, F-39) 또는 슬러그로 단일 팩트 레코드와 1차 출처 원문 발췌(excerpt)를 조회합니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
기준 시각(since) 이후 신규 등록·개정(v2)·만료 전환(expired)된 공개 팩트 변경 이력을 반환합니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| since | string | no | — |
| limit | integer | no | — |
발행된 블로그 리포트, 오리지널 웹소설, 웹툰, 영상 에피소드 메타데이터를 통합 검색합니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | — |
| type | string | no | — |
| category | string | no | — |
| limit | integer | no | — |
특정 아티클 슬러그가 인용한 모든 검증 팩트(F-xx)와 1차 공식 출처 계보를 반환합니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | no | — |
| keyword_or_slug | string | no | — |
오리지널 시리즈의 공식 세계관 설정(Lore)을 조회합니다. 무인증 요청에는 public/canon 레코드만 반환되며, internal_read 스코프 API 키가 제시된 경우에만 internal/draft 설정이 포함됩니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| series_id | string | no | — |
| series_slug | string | no | — |
| slug | string | no | — |
| entity_type | string | no | — |
archive.md 허브가 제공하는 공개 데이터셋, MCP 서버, 전문 에이전트 카탈로그를 조회합니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | no | — |
비식별 처리된 실제 드라이룸·클린룸·공조(HVAC)·산업플랜트·데이터센터(IDC) 프로젝트 표본(1,469건)과 설계팀·기술연구소·기술혁신센터 지식 카드(100건) 및 8대 사내 엔지니어링 자동화 계산 엔진(CAC v1.0.0, 더블로터 2-ROTOR 통합설계 Ver 2.0.1, 제습로터 Ø250~Ø2950 유효면적·시뮬레이션·AI-DHU SEED, 냉수코일 VBA 다항식, 도어 차압 오리피스 누기풍량, 덕트·판넬·국부제습기 CLD 840 물량산출, 버퍼탱크·공조펌프·냉각탑 보급수·제어밸브, 3상 380V 차단기·케이블트레이·IDC CRV4/PEX4/CRAH/FWU)을 기반으로 공정·원가·설계 계산치에 답합니다. 호출 시 Authorization: Bearer <API_KEY> 헤더가 필수입니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | — |
| work_type | string | no | — |
| industry | string | no | — |
공사 유형(드라이룸/클린룸/HVAC/EPC), 시공 면적(m²), 요구 성능 사양(노점 °C DP 또는 ISO 등급), 공종 범위를 입력받아 과거 수행 프로젝트 표본(1,469건)에서 총액·m²당 금액·착공~준공 공기(일)의 사분위 범위(p25, 중앙값, p75)와 공정 단계별 기간 비중 및 기본설계(FEED) 장비 용량을 산출합니다. 호출 시 Authorization: Bearer <API_KEY> 헤더가 필수입니다.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| work_type | string | yes | — |
| sub_type | string | no | — |
| area_m2 | number | yes | — |
| dew_point_c | number | no | — |
| iso_class | integer | no | — |
| scope | array | no | — |
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install archive.md MCP & Data Hub or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
The implementation source was not read — this reflects the declared tool metadata only.
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_facts | no tags | |
| search_verified_facts | no tags | |
| get_fact | no tags | |
| list_fact_changes | no tags | |
| search_content | no tags | |
| get_article_sources | no tags | |
| get_storyverse_lore | no tags | |
| list_catalog | no tags | |
| ask_construction_agent | no tags | |
| estimate_construction_range | no tags |
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 3.0.0.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish archive.md MCP & Data Hub can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.