Boundr

UK administrative boundary data from OS Boundary Line: name search, point lookup, GeoJSON geometries

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
88%
命名の品質
97%
ポイズニングのリスク
80%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(3)

  • HIGHTool poisoning patterns detected
  • LOWTool 'get_boundary_geojson_simplified' name length outside 3-30 rangeget_boundary_geojson_simplified 内
  • INFOTool description contains placeholder or incomplete textget_boundary_by_code 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,993トークン数(ツール定義)
~1.4 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 1.56%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "boundr": {
      "url": "https://mcp.boundr.dev/sse"
    }
  }
}

リモートエンドポイント

https://mcp.boundr.dev/ssesse
https://mcp.boundr.dev/mcpstreamable-http

できること

ツール一覧

ツール(7)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢list_boundary_type_codes

Returns every valid UK boundary type code mapped to its human-readable label. Call this before using any tool that accepts a `boundary_type` or `boundary_types` argument so you know which codes are legal. Passing an unlisted code to another tool raises a ValueError. Boundary type codes are stable Ordnance Survey identifiers. Common ones: - "CTY" → County - "LBO" → London Borough - "UTA" → Unitary Authority - "MTD" → Metropolitan District - "DIS" → District - "DIW" → District Ward - "CCTY" → Ceremonial County - "HCTY" → Historic County - "WMC" → Westminster Parliamentary Constituency - "GLC" → Greater London Constituency - "SWC" → Scotland/Wales Constituency - "PAR" → Parish - "CED" → County Electoral Division Returns: Dict mapping code → label for all supported boundary types, e.g. {"CTY": "County", "LBO": "London Borough", ...}

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "additionalProperties": {
    "type": "string"
  }
}
🟢search_boundaries_by_name(name, boundary_type)

Search for UK administrative boundaries by name (case-insensitive partial match). Use this to discover boundaries when you have a place name but not a code. Returns lightweight metadata only — no geometry. If you need to display or analyse the boundary shape, call get_boundary_geojson_by_code() with the returned `code`. Call list_boundary_type_codes() first if you need to filter by type and are unsure which code to use.

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Full or partial boundary name. Case-insensitive. Examples:\n  \"Hackney\", \"Greater Manchester\", \"York\", \"Kent\"."
    },
    "boundary_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional type code to narrow results, e.g. \"LBO\" for\n           London Boroughs or \"CTY\" for Counties. Must be a code\n           from list_boundary_type_codes(); raises ValueError otherwise."
    }
  },
  "required": [
    "name"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢find_boundaries_at_point(lat, lng, boundary_types)

Find all UK administrative boundaries that geographically contain a coordinate point. Use this to answer "what county/borough/ward is this location in?" for a latitude/longitude. Returns lightweight metadata only — no geometry. If you need to display a boundary shape, call get_boundary_geojson_by_code() with the returned `code`. Multiple boundaries at different administrative levels typically contain the same point (e.g. a ward, a borough, and a county). Filter by boundary_types to restrict which levels are returned. Call list_boundary_type_codes() first if you are unsure which type codes to use.

入力スキーマ

{
  "type": "object",
  "properties": {
    "lat": {
      "type": "number",
      "description": "Latitude in decimal degrees. Must be between -90 and 90.\n Example: 51.5074 (central London)."
    },
    "lng": {
      "type": "number",
      "description": "Longitude in decimal degrees. Must be between -180 and 180.\n Example: -0.1278 (central London)."
    },
    "boundary_types": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional list of type codes to restrict results,\n            e.g. [\"CTY\", \"LBO\"]. All levels are returned if omitted."
    }
  },
  "required": [
    "lat",
    "lng"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_boundary_by_code(code)

Look up metadata for a single UK boundary by its ONS census code. No geometry. Use this when you already have a census code (e.g. from search_boundaries_by_name() or find_boundaries_at_point()) and need structured metadata such as area size or type label. If you also need the boundary shape for display or analysis, call get_boundary_geojson_by_code() instead. ONS census codes (sometimes called GSS codes or LAU codes) are stable identifiers of the form "E09000012" (Hackney), "E10000016" (Kent), etc. The first letter indicates the country: E = England, W = Wales, S = Scotland, N = Northern Ireland.

入力スキーマ

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "ONS census / GSS / LAU code, e.g. \"E09000012\".\n  Case-insensitive — \"e09000012\" resolves to the same boundary."
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_boundary_geojson_by_code(code)

Fetch the full GeoJSON geometry for a UK boundary by its ONS census code. Returns a GeoJSON Feature object (WGS-84 / EPSG:4326) suitable for rendering on a map or performing geometric analysis. The geometry can be large — county and ceremonial county polygons are especially heavy. Only call this when you specifically need the shape; for metadata only use get_boundary_by_code() instead. IMPORTANT — Leaflet / web maps: use get_boundary_geojson_simplified() instead. The full geometry is large enough to exhaust your context window before you can finish writing the page. The simplified version is safe to embed directly in HTML and indistinguishable from the full shape at normal map zoom levels. Use this tool only when you need full-fidelity geometry for server-side analysis (e.g. precise point-in-polygon checks, area calculations, clipping). Obtain the census code from search_boundaries_by_name() or find_boundaries_at_point() before calling this.

入力スキーマ

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "ONS census / GSS / LAU code, e.g. \"E09000012\" for Hackney.\n  Case-insensitive."
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_boundary_geojson_simplified(code, tolerance)

Fetch simplified GeoJSON for a boundary by its ONS census code. Safe to embed directly in generated HTML map files. At the default tolerance (0.0001°) a constituency polygon shrinks from ~4,000 vertices to ~200–400 with no visible difference at normal map zoom levels. Prefer this over get_boundary_geojson_by_code() when writing Leaflet map pages — the full geometry is large enough to exhaust your context window before you can finish writing the HTML.

入力スキーマ

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "ONS census / GSS / LAU code, e.g. \"E14001592\" for Woking.\n  Case-insensitive."
    },
    "tolerance": {
      "default": 0.0001,
      "type": "number",
      "description": "Simplification tolerance in degrees (WGS-84). Default 0.0001.\n       Increase to 0.001 for county-scale boundaries."
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}
🟢get_boundary_bbox(code)

Get the bounding box and centroid for a boundary by its ONS census code. Returns min_lat, max_lat, min_lng, max_lng, centroid_lat, centroid_lng. Pass the bbox values directly to Knotsure's sightings_in_bbox() or geographic_summary(). Much cheaper than get_boundary_geojson_by_code() for spatial queries because no geometry is fetched or serialised.

入力スキーマ

{
  "type": "object",
  "properties": {
    "code": {
      "type": "string",
      "description": "ONS census / GSS / LAU code, e.g. \"E14001592\" for Woking.\n  Case-insensitive."
    }
  },
  "required": [
    "code"
  ],
  "additionalProperties": false
}

出力スキーマ

{
  "type": "object",
  "properties": {
    "result": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "result"
  ],
  "x-fastmcp-wrap-result": true
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 7 件
観測失敗バージョンは記録されていません—
検証済みバージョンは記録されていませんツール 7 件