mcpbeat Sign in

HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) MCP Server

by ogasurfproject-jpg Your server? Claim it
answering

HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) is answering right now. Last checked 9 min ago. It exposes 15 tools. Last commit 12 Oct 2026.

Public construction cost data for Japan and the U.S., each row with its source URL and licence.

Uptime history 10 days of history
10 days agonow
100.0%
Uptime 24h
92 of 92 checks
15
Tools
read from the server
58 ms
Response time
average over 24h
2
Stars
last commit 12 Oct 2026

What changed 1

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 4 October 2026. No other catalogue keeps this.

4 Oct a tool description was rewritten search_jccdb_items

What the code does

We read the source, 7 h ago · tools taken from the live server · rules ccca72095570

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Hidden recipient in outgoing message workers/hs-estimate/index.js:193 
        reply_to: '[email protected]',
Builds a file path from a variable data/jccdb-obs-v2/tools/migrate_v1.py:16, data/jccdb-obs-v2/tools/parsers/dbra_stage_to_raw.py:31, data/jccdb-obs-v2/tools/parsers/dbra_unpack.py:43 и ещё 31 
    return list(csv.DictReader(open(os.path.join(V1, "observations", fn), encoding="utf-8")))
Runs an external command data/jccdb-obs-v2/tools/parsers/check_mlit_gijutsusha_series.py:52, data/jccdb-obs-v2/tools/parsers/check_mlit_roumu_series.py:61, data/jccdb-obs-v2/tools/parsers/mlit_grid.py:22 и ещё 48 
    t8 = N(subprocess.run(["pdftotext", "-layout", os.path.join(OBS2, "raw", "mlit-gijutsusha-r8.pdf"), "-"], capture_output=True).stdout.decode())
Executes code built at runtime tools/jcs_conformance.mjs:35 
const canonicalJson = new Function(m[0] + "; return canonicalJson;")();
Runs an external command workers/hs-hearing/formanswer_test.mjs:192, workers/hs-hearing/run_all.mjs:49 
    const r = spawnSync(process.execPath, ["--check", js], { encoding: "utf8" });
Page executes code built at runtime admin-app/index.html:167, admin/index.html:153, ai-shain/index.html:466 и ещё 36 
  document.getElementById('main').innerHTML = fns[state.tab]();
Page loads a third-party script hs-reverse-estimate/index.html:244, souba/kanban-secchi-koji-hiyou/index.html:94, souba/nodate-kanban-secchi-hiyou/index.html:92 и ещё 2 
<script src="https://www.paypal.com/sdk/js?client-id=AVePXfDeP_YDUgmcFEJNjFHuYkbXZ-VQcLEecJs5Li2la9qDbtZJamy-iXzTxWlPdUODt6KNV3nqUKHP&currency=JPY&locale=ja_JP"></script>
Reads files and sends them to the network note-post/post_to_note.js:450, ops/jccdb_upgrade_20260926/itest_v2.mjs:41, ops/jccdb_upgrade_20260926/itest_v3.mjs:51 и ещё 4 
  for (const f of fs.readdirSync(feedDir)) {
Dumps the whole environment ops/jccdb_counts_v51/toshi_steps_counts.sh:149, ops/jccdb_counts_v51/update_counts.py:530 
env = dict(os.environ, GIT_OPTIONAL_LOCKS="0")
Sends data to a third-party sink verify-directory/survey/data/survey0_v4_2026-08-19.json:40, verify-directory/survey/data/survey0_v4_2026-09-01.json:44, verify-directory/survey/data/survey1_report_2026-08-23.json:89 
      "openings-vote-drilling-initially.trycloudflare.com",
Long encoded blob in source workers/a2a-card-sign/interop-matrix/vectors/a2a-card-sign-v01/s0-control/S0-001.json:15, workers/a2a-card-sign/interop-matrix/vectors/a2a-card-sign-v01/s0-control/S0-002.json:15, workers/a2a-card-sign/interop-matrix/vectors/a2a-card-sign-v01/s0-control/S0-003.json:15 и ещё 38 
  "canonical_utf8_hex": "7b226361706162696c6974696573223a7b22707573684e6f74696669636174696f6e73223a66616c73652c2273747265616d696e67223a747275657d2c2264656661756c74496e7075744d6f646573223a5b22746578742f706c61696e225d2c2264656661756c744f75747075744d6f646573223a5b22746578742f706c616…
In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

CI pipeline leaks secrets outward .github/workflows/blog-post.yml:49 
            curl -s -X POST -H "Authorization: Bearer ${{ secrets.GITHUB_TOKEN }}" -H "Accept: application/vnd.github+json" https://api.github.com/repos/${{ github.repository }}/actions/workflows/static.yml/dispatches -d '{"ref":"main"}'

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

run in your terminal
claude mcp add construction-cost-data --transport http https://ccdb.horizonshield.dev/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "construction-cost-data": {
      "url": "https://ccdb.horizonshield.dev/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.construction-cost-data]
url = "https://ccdb.horizonshield.dev/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "construction-cost-data": {
      "url": "https://ccdb.horizonshield.dev/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "construction-cost-data": {
      "url": "https://ccdb.horizonshield.dev/mcp"
    }
  }
}

Available tools 15

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

jccdb
get_jccdb_coverage
JCCDB の観測層に何がどこまであるかを返す: 国 x 種類(layer) x 出典の件数、値のある件数、状態別、出典の時点。0 行の組み合わせは absent に『無い(取り込んでいない)』と明記する。答える前に、その国・種類のデータがあるかをここで確かめる。 / What the JCCDB observation layer holds: rows per country x layer x source, priced rows, status counts and source periods; empty combinations are listed as absent (not ingested).
get_jccdb_index_series
建設費の指数(NHCCI、PPI、建設工事費デフレーター等)の系列を期間で返し、前年同期比を添える。前年同期比はこのサービスが計算した値(computed:true)で、原本には無い。query も source_id も無いときは系列の一覧。例: query='NHCCI', from='2020Q1'。 / Construction cost index series over a period with year-over-year change computed by this service (computed:true). Without query or source_id, lists the series.
get_jccdb_labor_rate
国交省の公共工事設計労務単価(47都道府県 x 50職種、所定労働時間内8時間あたりの賃金)を引く。既定は地域ごとの最新の時点、history:true で年ごとの系列。例: pref='奈良県', job='大工'。 / MLIT public-works design labor rates by prefecture and trade (wage per 8 hours); latest by default, yearly series with history:true.
get_jccdb_observations
品目が『どの地域・地区で・いつ・いくらで(または非公開の理由)』公的資料に載っているかを返す(日本と米国)。値は再配布を許す出典のときだけ入り、各行に license・attribution・evidence_url が付く。県が刊行物単価を使って値を公開していない地区は publication_based_not_public と返す(欠落ではなく事実)。例: query='生コンクリート', pref='奈良県'。公共工事の設計単価であり、リフォームの見積単価ではない。 / Region, date and price status of an item in Japanese and U.S. public documents. Values only where the licence allows redistribution; every row carries licence, attribution and evidence URL; cells where the public body uses commercial price publications are reported as such, not guessed.
get_jccdb_work_unit_price
工事の単価(材料・労務・機械の複合。施工パッケージ型積算の標準単価など)を引き、構成比の行を同じパッケージの行に添えて返す。公共土木の積算単価であり、リフォームの見積単価ではない。例: query='掘削', pref='東京都'。 / Public-works unit prices for work items (materials, labor and equipment combined), with composition-ratio rows attached to their package. Not renovation quote prices.
search_jccdb_items
日本の建設費オープンデータ JCCDB(v5.1 は計526,128件)の品目の目録(95,403)を名前で探す。生コン・異形棒鋼・ヒューム管・側溝など資材や製品、労務の品目が公的資料に実在するかと証拠URLを返す。工事カテゴリ(search_cost_category)に無い資材はこちら。地域・時点・価格は get_jccdb_observations。 / Search the JCCDB item catalogue (95,403 line items of the 526,128 records in v5.1; materials, products, labor) by name; returns whether each exists in a public document, with its evidence URL. Use for materials that are not renovation work categories.
area
get_us_area_factor
米国の場所ごとの建設費の係数を引く: 国防総省の Area Cost Factor と Sustainment ACF(軍の施設ごと、96 基準都市の平均 = 1.00)と、陸軍工兵隊 CWCCIS の州の調整係数(現行値と年ごと)。geo は州・郡・ZIP(zip:28533)・市(Cherry Point, NC)・国外の国(country:JP)。中央値は computed:true。予算用の係数で、見積の良し悪しを判定する係数ではない。 / U.S. location cost factors: DoD Area Cost Factors by installation (96 base-city average = 1.00) and USACE CWCCIS state adjustment factors; geo accepts state, county, ZIP, city or an overseas country. Budgeting factors, not a test of whether a quote is fair.
compare
compare_jccdb_regions
品目と規格で、地域ごとの最新時点の値を並べ、最小・中央・最大と状態別の件数を返す。規格・単位・値の種類が同じものだけを比べる(普通と高炉は別の組)。中央値はこのサービスの計算(computed:true)。例: query='生コンクリート', spec='24-8-25(20)', layer='material', normalize='namacon'(局ごとの規格の書き方の違いを越えて束ねる)。 / Latest value per region for an item and spec, with min, median (computed) and max and counts by price status; only identical spec, unit and basis are compared.
construction
get_us_construction_prices
米国の公的な建設費データベースを layer・地域・時点・品目で引く: labor(Davis-Bacon の法定賃金)、wage(BLS OEWS・QCEW の賃金)、work(DoD・FTA の単価)、equipment(FEMA・USACE の機械損料)、index(PPI・NHCCI・CWCCIS・DoD の地域係数)、spending(Census の工事支出と建築許可、市の許可)、cost_sqft(面積あたり工事費)、cost_limit(HUD の 1 戸あたり上限)、bid_item(州 DOT の入札単価)、house_price、material。geo は州・郡 FIPS(county:06037)・都市圏(cbsa:31080)・市(Austin, TX)。州を指定すると全国一律の行と USACE の地域の行も添える。1m2 あたりへの換算は computed:true。住宅リフォームの見積単価ではない。 / The U.S. public construction cost database by layer, region (state, county FIPS, CBSA, place), period and item: Davis-Bacon prevailing wages, BLS wages, public unit costs, equipment rates, permits and spending, indexes and area factors, HUD cost limits and state DOT bid prices. National and USACE regional rows are added for a state; per-m2 conversions are computed:true. Not residential remodeling quotes.
contract
get_us_contract_discounts
州と共同購買の契約書が公開している、定価からの値引き率を返す(ワシントン州 DES 23623 配管部材・11121 電気資材、NASPO ValuePoint の資材 MRO の Grainger・Fastenal・MSC・Lawson・HD Supply、Home Depot の塗料)。掛け率 = 1 - 値引き率(computed:true)。定価への上乗せ(Over MSRP)と業者の目録からの値引き(Catalog Off)は別の列で、掛け率には入れない。率は上限で、定価の基準は行ごとに違う。例: query='eaton breakers'。 / Published discount rates off list price in U.S. public contracts (Washington DES plumbing and electrical, NASPO ValuePoint MRO), with kake_ratio = 1 - discount (computed:true). Over-MSRP and catalog-off rows are kept separate. Rates are ceilings; list bases differ by row.
import
get_us_import_landed_cost
米国に輸入される建材と化学品の陸揚げ原価を HS 10 桁で返す(Census の輸入統計 IMDB、月と年初来): 通関価格・CIF・計算上の関税(232 条などの追加関税を含む)・数量・単価・実効の関税率と、相手国の上位(か country で指定の国)。単価と実効の関税率は computed:true。国内の運賃と通関の手数料は入らない。 / Landed cost of U.S. imports of construction materials and chemicals by HS 10-digit code (Census IMDB, month and year to date): customs value, CIF, calculated duty (including Section 232 and other additional duties), quantity, unit cost and effective duty rate (computed), with top partner countries or one country.
permits
get_us_permits
米国の建築許可を地域と年で引く: Census Building Permits Survey(州・郡・都市圏・市の棟数・戸数・工事額・1戸あたり)と、市の許可データの申告工事額の分布(件数・合計・中央値・25/75 分位・1 sqft あたり)。工事額は申請者の申告で、契約額でも見積の単価でもない。計算した値は computed:true。例: geo='Austin, TX', year='2024'。 / U.S. building permits by region and year: Census BPS buildings, units, valuation and per-unit values, plus distributions of declared valuations in city permit data (median, quartiles, per sq ft). Declared by applicants; not contract prices or quotes.
prevailing
get_us_prevailing_wage
米国 Davis-Bacon 法の一般賃金決定(連邦の資金が入る建設工事で払うべき最低の基本時給と付加給付)を、州・郡・職種で引く。1 件ごとに基本時給と付加給付を並べ、決定番号・改訂・公表日・郡の一覧・出典 URL を添える。基本 + 付加給付の合計は computed:true。民間の住宅工事の相場や業者の請求単価ではない。例: state='CA', county='Los Angeles', trade='carpenter'。 / U.S. Davis-Bacon general wage determinations by state, county and trade: base wage and fringe side by side with decision number, revision, publication date and source URL; the total is computed:true. These are minimums for federally funded work, not private market rates.
price
get_us_price_chain
米国で建材や化学品が流通の各段でいくらになるかを計算して返す: 輸入の陸揚げ原価(Census の輸入統計、CIF + 関税、232 条などの追加関税を含む)から、卸(業種の平均の粗利率、Census AIES 2024)、小売(直接輸入と卸経由の幅)、元請(Caltrans の材料の上乗せ 15%)まで。HS 10 桁か英語の品名で引く。各行に式・出典の URL と sha256・卸の業種の当て方の確度・BEA 2007 の流通構造との照合が付く。推計(computed:true)で、見積の良し悪しを判定する値ではない。例: query='plywood'、hs='2523290000'(ポルトランドセメント)。 / Estimated U.S. prices along the distribution chain for construction materials and chemicals: landed import cost (Census, CIF plus duty including Section 232) to wholesale (industry-average gross margin, Census AIES 2024), retail (range: direct import vs via wholesale) and contractor (Caltrans materials markup 15%). Look up by HS code or English product name; every row carries the formula, source URLs and hashes, mapping confidence and a BEA 2007 cross-check. Estimates (computed:true), not a verdict on any quote.
trade
get_us_trade_margins
米国の卸と小売の粗利率を NAICS で返す(Census AWTS 1992〜2022、ARTS 1993〜2022、AIES 2024)。kake_cost_ratio = 1 - 粗利率(売値のうち仕入れ原価の割合)。commodity か include_bea で BEA 2007 の建設業と家計の購入の流通構造(生産者価格・運賃・卸・小売・購入者価格)も。業種の平均で、個々の会社の仕入れ値ではない。例: naics='4233'(建材卸)、naics='444110'(ホームセンター)。 / U.S. wholesale and retail gross margins by NAICS (Census AWTS, ARTS, AIES 2024) with kake_cost_ratio = 1 - margin; optionally the BEA 2007 margin structure. Industry averages, not any firm's cost.

Endpoints

URLTransportStateLatencyChecked
https://ccdb.horizonshield.dev/mcp streamable-http answering 44 ms 9 min ago

Alternatives to HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States)

same job, measured the same way
HORIZON SHIELD: construction and renovation estimate auditor
by ogasurfproject-jpg

Fair-price checks for Japanese renovation quotes, with sources and recomputable records.

15 tools answering
PadelTrue padel racket data
by odedkovach

Published padel racket specifications, each with its source, and calculated ratings. Read only.

5 tools answering
Jhnrd
by ogasurfproject-jpg

Japan home-visit nursing reimbursement rules, each with its source and that source's standing.

11 tools answering
Agam
by ashwingopalsamy-home

Keyless public journal reads: construction costs, day-wise work, source precision and exact INR.

2 tools answering
LinkList
by linklist

Search source collections your team vetted. Every passage cites its URL and fetch date.

answering
open-signals
by civops-platform

Public hazard, water, weather and EPA data with source, age and licence on every reading.

9 tools answering
StatsMapped Public Data
by statsmapped

Public statistics for Ireland and the UK: housing, crime, health, economy, welfare, with caveats.

1 002 installs/wk 4 tools answering
Radicado Uno
by radicadouno

Colombian company and procurement data by NIT, each field with its official source. Free checks.

20 tools answering

HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) — questions

Answers built from our own checks of this server.

What can HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) do?
It exposes 15 tools, read directly from the server on our last check. Among them: compare_jccdb_regions, get_jccdb_coverage, get_jccdb_index_series, get_jccdb_labor_rate, get_jccdb_observations, get_jccdb_work_unit_price and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 58 ms. The bar chart above shows every period we have measured.
How do I connect HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States)?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) need an API key?
No. HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States)?
It answers our handshake in 58 ms on average, which is faster than 93% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is HORIZON SHIELD Construction Cost Data: JCCDB (Japan) and USCCDB (United States) open source?
Yes — it is published under the MIT licence, written in HTML, 2 stars on GitHub and 14 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.