City Atlas 城市圖譜

Greater Hsinchu, Taiwan open data on a 125 m grid: crashes, buses, schools, flood. Read-only.

Should I use this

Description quality

72%

Schema completeness

99%

Naming quality

86%

Poisoning risk

100%

Permission match

100%

Protocol compliance

100%

Findings (6)

LOWTool 'describe_metric' description lacks action verbin describe_metric
LOWTool 'rank' description lacks action verbin rank
LOWTool 'need_ranking' description lacks action verbin need_ranking
LOWTool 'overlay_metrics' description lacks action verbin overlay_metrics
LOWTool 'compare_groups' description lacks action verbin compare_groups
LOWTool 'compare_change' description lacks action verbin compare_change

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~4,335Tokens (tool definitions)

~1.6 KBTypical response size

Significant attention impact (3.39% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

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

Remote endpoints

https://mcp.cityatlas.tw/mcpstreamable-http

What it can do

Tool inventory

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).

Input Schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "關鍵字,例:「事故 行人」「公車」「淹水」;空白分開的字要全部對上"
    },
    "limit": {
      "description": "最多幾條,預設 12",
      "type": "integer",
      "minimum": 1,
      "maximum": 40
    }
  },
  "required": [
    "query"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "metric": {
      "type": "string",
      "description": "資料代號或名稱,例:crash_ped4 或「行人事故」"
    }
  },
  "required": [
    "metric"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "metric": {
      "type": "string",
      "description": "資料代號或名稱,例:crash_ped4 或「行人事故」"
    },
    "unit": {
      "description": "單位:里(預設,neighbourhood)或 鄉鎮(district)",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "per": {
      "description": "換算:不除(預設)/ 每千居民 / 每公里道路 / 路 + 人 + 店 / 分母的資料代號",
      "type": "string"
    },
    "town": {
      "description": "只看一個鄉鎮,例:竹北、東區",
      "type": "string"
    },
    "filters": {
      "description": "篩條件:里 / 鄉鎮的值要符合,例:[{metric:'residents',op:'>',value:100}]",
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "metric": {
            "type": "string"
          },
          "op": {
            "type": "string",
            "enum": [
              ">",
              "<",
              ">=",
              "<="
            ]
          },
          "value": {
            "type": "number"
          }
        },
        "required": [
          "metric",
          "op",
          "value"
        ]
      }
    },
    "descending": {
      "description": "由高到低,預設 true",
      "type": "boolean"
    },
    "top": {
      "description": "前幾名,預設 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    },
    "shrink": {
      "description": "有換算時,人少的地方往平均拉;預設 true(同網站),false = 看原始的率",
      "type": "boolean"
    }
  },
  "required": [
    "metric"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "place": {
      "type": "string",
      "description": "地址、里名或鄉鎮名"
    },
    "metrics": {
      "description": "要看哪幾條(代號或名稱);不給就看常用的 10 條",
      "maxItems": 12,
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "place"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "unit": {
      "description": "單位:里(預設,neighbourhood)或 鄉鎮(district)",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "weights": {
      "description": "權重;不帶 = 60 / 20 / 10 / 10",
      "type": "object",
      "properties": {
        "pm": {
          "description": "被耽誤的人·分鐘",
          "type": "number",
          "minimum": 0
        },
        "jobs": {
          "description": "工作地",
          "type": "number",
          "minimum": 0
        },
        "school": {
          "description": "學校",
          "type": "number",
          "minimum": 0
        },
        "civic": {
          "description": "公共設施",
          "type": "number",
          "minimum": 0
        }
      }
    },
    "town": {
      "description": "只看一個鄉鎮,例:竹北、東區",
      "type": "string"
    },
    "top": {
      "description": "前幾名,預設 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "metric_a": {
      "type": "string",
      "description": "資料 A(代號或名稱)"
    },
    "metric_b": {
      "type": "string",
      "description": "資料 B(代號或名稱)"
    },
    "per": {
      "description": "A 的換算:不除(預設)/ 每千居民 / 每公里道路 / 路 + 人 + 店",
      "type": "string"
    },
    "unit": {
      "description": "單位:里(預設,neighbourhood)或 鄉鎮(district)",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "town": {
      "description": "只看一個鄉鎮,例:竹北、東區",
      "type": "string"
    },
    "top": {
      "description": "前幾名,預設 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    },
    "shrink": {
      "description": "有換算時,人少的地方往平均拉;預設 true(同網站),false = 看原始的率",
      "type": "boolean"
    }
  },
  "required": [
    "metric_a",
    "metric_b"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "metric_a": {
      "type": "string",
      "description": "要比的東西 A(件數 / 長度這類能加總的),例:行人事故"
    },
    "has_b": {
      "type": "string",
      "description": "分組的依據 B:格裡有沒有,例:人行道、公車站"
    },
    "per": {
      "description": "A 的換算:不除(預設)/ 每千居民 / 每公里道路",
      "type": "string"
    }
  },
  "required": [
    "metric_a",
    "has_b"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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.

Input Schema

{
  "type": "object",
  "properties": {
    "conditions": {
      "minItems": 1,
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "metric": {
            "type": "string",
            "description": "資料代號或名稱,例:crash_ped4 或「行人事故」"
          },
          "op": {
            "type": "string",
            "enum": [
              ">",
              "<",
              ">=",
              "<=",
              "有",
              "沒有"
            ],
            "description": "比較方式;「有」= > 0、「沒有」= 0"
          },
          "value": {
            "description": "> < >= <= 才要給",
            "type": "number"
          }
        },
        "required": [
          "metric",
          "op"
        ]
      },
      "description": "每一格都要同時符合,例:[{metric:'stop_dist_m',op:'>',value:500}]"
    },
    "unit": {
      "description": "單位:里(預設,neighbourhood)或 鄉鎮(district)",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "town": {
      "description": "只看一個鄉鎮,例:竹北、東區",
      "type": "string"
    },
    "top": {
      "description": "前幾名,預設 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    }
  },
  "required": [
    "conditions"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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).

Input Schema

{
  "type": "object",
  "properties": {
    "topic": {
      "type": "string",
      "enum": [
        "population",
        "crash",
        "income",
        "turnout_president",
        "turnout_party_list",
        "turnout_legislator",
        "turnout_mayor"
      ],
      "description": "題目:population 里人口 / crash 事故 / income 里所得中位數 / turnout_president 總統投票率 / turnout_party_list 不分區政黨票投票率 / turnout_legislator 立委(區域)投票率 / turnout_mayor 縣市長投票率"
    },
    "from": {
      "description": "起始年份,例:107(人口)、111(事故)、2020(投票率,選舉年);不給 = 預設(投票率是最近兩屆)",
      "type": "string"
    },
    "to": {
      "description": "結束年份;不給 = 預設最後一年",
      "type": "string"
    },
    "threshold": {
      "description": "門檻:增加(或減少)幾人 / 件 / 萬元 / 個百分點以上才算「很多」;不給或給 0 = 預設(人口 500、事故里 5 鄉鎮 20、所得 5、投票率 3)",
      "type": "number",
      "minimum": 0
    },
    "unit": {
      "description": "單位:里(預設)或 鄉鎮;只有事故兩種都可以,其他只比里",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "top": {
      "description": "前幾名,預設 10",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    }
  },
  "required": [
    "topic"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

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).

Input Schema

{
  "type": "object",
  "properties": {
    "metric": {
      "type": "string",
      "description": "資料代號、名稱,或「需要度」"
    },
    "per": {
      "description": "換算:不除(預設)/ 每千居民 / 每公里道路 / 路 + 人 + 店 / 分母的資料代號",
      "type": "string"
    },
    "town": {
      "description": "地圖先對準這個鄉鎮(其他鄉鎮照樣畫)",
      "type": "string"
    },
    "unit": {
      "description": "單位:里(預設,neighbourhood)或 鄉鎮(district)",
      "type": "string",
      "enum": [
        "里",
        "鄉鎮"
      ]
    },
    "shrink": {
      "description": "有換算時,人少的地方往平均拉;預設 true(同網站),false = 看原始的率",
      "type": "boolean"
    }
  },
  "required": [
    "metric"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}

Community

Rate this Server

Evidence

Recent observations

Oct 16, 2026, 11:04 PM UTCverifiedversion not recorded10 tools

City Atlas 城市圖譜

Quality & Safety

Findings (6)

Context Cost

One-Click Install

Remote endpoints

Tool inventory

Tools (10)

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Input Schema

Rate this Server

Recent observations