Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "cityatlas": {
      "type": "http",
      "url": "https://mcp.cityatlas.tw/mcp"
    }
  }
}

claude mcp add --transport http cityatlas https://mcp.cityatlas.tw/mcp

[mcp_servers.cityatlas]
url = "https://mcp.cityatlas.tw/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cityatlas": {
      "type": "remote",
      "url": "https://mcp.cityatlas.tw/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "cityatlas": {
      "type": "http",
      "url": "https://mcp.cityatlas.tw/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=cityatlas&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vbWNwLmNpdHlhdGxhcy50dy9tY3AifQ%3D%3D"
}

{
  "servers": {
    "cityatlas": {
      "type": "http",
      "url": "https://mcp.cityatlas.tw/mcp"
    }
  }
}

{
  "mcpServers": {
    "cityatlas": {
      "httpUrl": "https://mcp.cityatlas.tw/mcp"
    }
  }
}

extensions:
  "cityatlas":
    enabled: true
    name: "cityatlas"
    type: streamable_http
    uri: "https://mcp.cityatlas.tw/mcp"
    timeout: 300

Quality 94 / 100new

protocol88 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
warn
protocol.list_ttltools/list declares ttlMs 0, so clients re-fetch it on every use

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations10 of 10 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 2,147 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 6 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

10 tools, about 2,147 tokens to load them all · tool set 4f907fc7536d · tools last changed 2026-10-18 · checked 2026-10-21 01:38 UTC

Tool changes

2026-10-18compare_changechangeddescription, input schema
before
兩個年份比,哪些里增加最多、減少最多(跟網站 07「看變化」同一套):里人口(107–114 年底,戶籍)、事故場數(111–114)、里所得中位數(111→112)、投票率(總統 / 立委不分區政黨票 / 立委區域 / 縣市長,年份照選舉目錄)。門檻自己填(增加幾人 / 件 / 萬元 / 個百分點以上才算增加很多);里界調整過、兩屆不是同一塊地的里不比、列出原因。只描述差多少,不做因果。Which neighbourhoods grew or shrank most between two years (population, crashes, income, turnout).
after · 85% of words in common
兩個年份比,哪些里增加最多、減少最多(跟網站 07「看變化」同一套):里人口(97–114 年底,戶籍;97–106 只有新竹縣市、竹南、頭份,新設里設立前是估計、不拿來比)、事故場數(111–114)、里所得中位數(111→112)、投票率(總統 / 立委不分區政黨票 / 立委區域 / 縣市長,年份照選舉目錄)。門檻自己填(增加幾人 / 件 / 萬元 / 個百分點以上才算增加很多);里界調整過、兩屆不是同一塊地的里不比、列出原因。只描述差多少,不做因果。Which neighbourhoods grew or shrank most between two years (population, crashes, income, turnout).
2026-10-18search_catalogchangeddescription
before
用關鍵字找城市圖譜的資料:11 大類 80 項資料,細到 159 條指標(139 條格網:事故、公車、人行道、淹水、樹…;20 條里 / 鄉鎮 / 縣市:里人口、長者與兒童、里所得…),加上 47 屆選舉與公投(投票率、得票率);公開版少 Google 街景判讀的 2 項 4 條,實際查得到 78 項、155 條:回代號、名稱、單位、年份、出處機關、是不是推估、涵蓋幾區。Search the indicator catalog by keyword (80 datasets in 11 categories, 159 indicators: 139 grid + 20 neighbourhood/district/county, plus 47 elections; this public server omits 4 Street-View-derived indicators, so 155 are searchable).
after · 81% of words in common
用關鍵字找城市圖譜的資料:11 大類 82 項資料,細到 161 條指標(141 條格網:事故、公車、人行道、淹水、樹…;20 條里 / 鄉鎮 / 縣市:里人口、長者與兒童、里所得…),加上 47 屆選舉與公投(投票率、得票率);公開版少 Google 街景判讀的 2 項 4 條,實際查得到 80 項、157 條:回代號、名稱、單位、年份、出處機關、是不是推估、涵蓋幾區。Search the indicator catalog by keyword (82 datasets in 11 categories, 161 indicators: 141 grid + 20 neighbourhood/district/county, plus 47 elections; this public server omits 4 Street-View-derived indicators, so 157 are searchable).

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-7d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://mcp.cityatlas.tw/mcp` streamable-http	none	yes	100%	530 ms	2026-07-28	2026-10-21

Tools (10)

`compare_change`read-only	兩個年份比,哪些里增加最多、減少最多(跟網站 07「看變化」同一套):里人口(97–114 年底,戶籍;97–106 只有新竹縣市、竹南、頭份,新設里設立前是估計、不拿來比)、事故場數(111–114)、里所得中位數(111→112)、投票率(總統 / 立委不分區政黨票 / 立委區域 / 縣市長,年份照選舉目錄)。門檻自己填(增加幾人 / 件 / 萬元 / 個百分點以上才算增加很多);里界調整過、兩屆不是同一塊地的里不比、列出原因。只描述差多少,不做因果。Which neighbourhoods grew or shrank most between two years (population, crashes, income, turnout).
`compare_groups`read-only	有 B 的格 vs 沒有 B 的格,A 差多少 —— 在居民 × 道路長度切成的 25 層裡各比一次(避免被市中心拉著走)。只描述,不做因果。Compare cells with vs without B, within strata of residents and road length.
`describe_metric`read-only	一條資料的完整出處(機關、資料集、網址、取得日、檔案、對帳)、涵蓋哪些鄉鎮、統計、以及「可能在講別的事」的但書。Full provenance and caveats of one indicator.
`filter_cells`read-only	找出同時符合最多四個條件的 125 公尺格,回符合幾格、住了多少人,並照里 / 鄉鎮加總。例:離公車站超過 500 公尺、又住超過 100 人。Find grid cells that meet up to four conditions.
`lookup_place`read-only	給地址(例:竹北市光明六路 10 號)、里名(例:竹北市東平里)或鄉鎮名 → 那裡各項數字,以及在大新竹排第幾;查里名時另附里人口、所得、65 歲以上與 14 歲以下。地址只定位到 125 公尺的格(用我們自己的門牌檔比對,不送外部服務、不記錄)。Numbers for an address, neighbourhood or district.
`need_ranking`read-only	哪裡最多人被公車耽誤(被耽誤的人·分鐘、工作地、學校、公設的百分位加權);權重可帶,不帶用預設 60/20/10/10。Where the most people lose time on public transport compared with driving.
`overlay_metrics`read-only	兩條資料疊起來看:A(可換算)與 B 各切三等分成九宮格,回各格有幾個里 / 鄉鎮,並列出「兩樣都高」的。例:事故(每千居民)高、人行道少的里。Which places are high on two indicators at once.
`rank`read-only	某條資料在里或鄉鎮排前幾名(跟網站 07 同一套算法:先加總再除、人少的地方往平均拉)。可換算每千居民 / 每公里道路 / 路 + 人 + 店(只有事故)/ 任何能當分母的代號;可只看某個鄉鎮、可加篩條件。只回前 N 名。里層資料(長者占比、里所得、選舉投票率…)一個里一個數,不能換算、單位只能是里(人數可加到鄉鎮)。沒編里的範圍不進排名。Rank neighbourhoods or districts by an indicator, optionally normalised.
`search_catalog`read-only	用關鍵字找城市圖譜的資料:11 大類 82 項資料,細到 161 條指標(141 條格網:事故、公車、人行道、淹水、樹…;20 條里 / 鄉鎮 / 縣市:里人口、長者與兒童、里所得…),加上 47 屆選舉與公投(投票率、得票率);公開版少 Google 街景判讀的 2 項 4 條,實際查得到 80 項、157 條:回代號、名稱、單位、年份、出處機關、是不是推估、涵蓋幾區。Search the indicator catalog by keyword (82 datasets in 11 categories, 161 indicators: 141 grid + 20 neighbourhood/district/county, plus 47 elections; this public server omits 4 Street-View-derived indicators, so 157 are searchable).
`show_map`read-only	把一條資料(或「需要度」)畫成里 / 鄉鎮的五級地圖,在對話裡直接顯示,可拖曳縮放、滑過看數字;換算同「排名」。畫不出來的 AI 會拿到一個能點開的網址(請轉給使用者)。Draw an indicator as an interactive choropleth map of neighbourhoods; chats that cannot render it get a link that opens the map in a browser (pass it on to the user).

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "tw.cityatlas/cityatlas",
  "title": "City Atlas 城市圖譜",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://mcp.cityatlas.tw/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.3.1",
  "websiteUrl": "https://mcp.cityatlas.tw/",
  "description": "Greater Hsinchu, Taiwan open data on a 125 m grid: crashes, buses, schools, flood. Read-only."
}