Planslurpen MCP Server

Planslurpen MCP Server

Enables interaction with Planslurpen, a Norwegian service that uses AI to interpret zoning and regulation plans. Supports retrieving plan data, looking up plans by property address, downloading plan provisions, and filtering structured plan information.

Category
访问服务器

README

Planslurpen MCP Server

A Model Context Protocol (MCP) server for interacting with Planslurpen, a Norwegian service that uses AI to interpret zoning and regulation plans (reguleringsplaner).

About Planslurpen

Planslurpen is a beta service from Direktoratet for byggkvalitet that provides machine-based interpretation of Norwegian regulation plans. It uses artificial intelligence to extract parameters from regulation plans, split by sub-areas (delområder) when available. The goal is to provide structured plan information for systems that need it.

Features

This MCP server provides tools to:

  • Retrieve plan interpretations by kommune number and plan ID
  • Look up plans by property address using cadastral numbers
  • Download plan outputs in JSON and XML (NPAD) formats
  • Get available fields and classifications for filtering
  • Access plan provisions (planbestemmelser) - the original legal text
  • Flexible response formats (JSON or Markdown)

Installation

Prerequisites

  • Python 3.10 or higher
  • pip

Setup

  1. Clone or download this directory

  2. Install dependencies:

pip install -r requirements.txt
  1. Make the server executable (optional):
chmod +x planslurpen_mcp.py

Usage

Running the Server

The server can be run directly:

python planslurpen_mcp.py

Claude Desktop Configuration

Add this to your Claude Desktop configuration file:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "planslurpen": {
      "command": "python",
      "args": ["/absolute/path/to/planslurpen_mcp/planslurpen_mcp.py"]
    }
  }
}

Replace /absolute/path/to/planslurpen_mcp/ with the actual path to this directory.

Available Tools

1. planslurpen_get_plan

Retrieve AI-interpreted plan data by kommune number and plan ID.

Parameters:

  • kommunenummer (required): 4-digit kommune number (e.g., "1106" for Haugesund)
  • plan_id (required): Plan identifier (e.g., "RL791")
  • versjon (optional): Specific version number
  • response_format (optional): "json" or "markdown" (default: "json")

Example:

Get plan interpretation for Haugesund kommune 1106, plan RL791, version 3

2. planslurpen_get_plan_by_id

Retrieve plan data by its UUID.

Parameters:

  • plan_uuid (required): UUID of the plan
  • response_format (optional): "json" or "markdown"

3. planslurpen_get_plan_output_json

Download complete plan output in JSON format with optional filtering.

Parameters:

  • kommunenummer (required): Kommune number
  • plan_id (required): Plan ID
  • versjon (optional): Version number
  • felt_kode (optional): Field code to filter (e.g., "byggehøyde", "utnyttingsgrad")
  • klassifikasjoner (optional): List of classifications to filter
  • response_format (optional): "json" or "markdown"

Tip: Call planslurpen_get_plan_fields first to see available filters!

4. planslurpen_get_plan_fields

Get list of available fields and classifications for a plan.

Parameters:

  • kommunenummer (required): Kommune number
  • plan_id (required): Plan ID
  • versjon (optional): Version number
  • response_format (optional): "json" or "markdown"

Use case: Call this first to discover what filters you can use in other tools.

5. planslurpen_get_plan_provisions

Download plan provisions (planbestemmelser) - the original legal text.

Parameters:

  • kommunenummer (required): Kommune number
  • plan_id (required): Plan ID
  • versjon (optional): Version number

6. planslurpen_get_plan_output_xml

Download plan output in NPAD XML format.

Parameters:

  • kommunenummer (required): Kommune number
  • plan_id (required): Plan ID
  • versjon (optional): Version number

7. planslurpen_lookup_property

Look up regulation plans for a specific property by its cadastral address.

Parameters:

  • kommunenummer (required): Kommune number
  • gardsnummer (required): Farm/cadastral number
  • bruksnummer (required): Parcel number
  • festenummer (optional): Leasehold number
  • seksjonsnummer (optional): Section number
  • response_format (optional): "json" or "markdown"

Example:

Look up plans for property 1106-45-123

Example Queries

Here are some example queries you can try with Claude:

  1. Get a plan interpretation:

    "Get the plan interpretation for Haugesund kommune 1106, plan RL791, version 3"

  2. Look up a property:

    "What regulation plans apply to property 1106-45-123 in Haugesund?"

  3. Explore available data:

    "What fields and classifications are available for plan RL791 in kommune 1106?"

  4. Get filtered data:

    "Get the byggeh høyde (building height) data for plan 1106/RL791"

Norwegian Terms

  • Kommune: Municipality
  • Reguleringsplan: Zoning/regulation plan
  • Planbestemmelser: Plan provisions (legal text)
  • Delområde: Sub-area within a plan
  • Gardsnummer: Farm/cadastral number
  • Bruksnummer: Parcel number
  • Festenummer: Leasehold number
  • Seksjonsnummer: Section number
  • Utnyttingsgrad: Utilization degree/floor area ratio
  • Byggehøyde: Building height
  • NPAD: Norwegian Planning Data (XML standard)

API Information

  • Base URL: https://planslurpen.no/api
  • Swagger Documentation: https://planslurpen.no/api/swagger/index.html
  • Website: https://planslurpen.no/

Character Limits

The server implements a 25,000 character limit on responses. If responses are truncated:

  • Use the planslurpen_get_plan_fields tool to see available filters
  • Apply filters using felt_kode or klassifikasjoner parameters
  • Request specific fields instead of full output

Error Handling

The server provides clear, actionable error messages:

  • 404 Not Found: Plan doesn't exist - verify kommune number and plan ID
  • 400 Bad Request: Invalid parameters - check parameter format
  • Timeout: Response too large - use filters to reduce size
  • Network errors: Connection issues - check internet connection

Development

This server follows MCP best practices:

  • Uses Pydantic v2 for input validation
  • Implements proper error handling with descriptive messages
  • Supports multiple response formats (JSON and Markdown)
  • Includes character limits and truncation
  • All tools are read-only and idempotent
  • Comprehensive docstrings and type hints

Beta Notice

Planslurpen is currently in beta. The quality of AI interpretation may vary, and the service is actively seeking feedback. If you encounter issues or have feedback about the interpretation quality, visit https://planslurpen.no/ to report it.

License

This MCP server is provided as-is for use with Planslurpen API. Please refer to Planslurpen's terms of service for API usage restrictions.

Links

  • Planslurpen Website: https://planslurpen.no/
  • MCP Documentation: https://modelcontextprotocol.io/
  • Example Plan: https://planslurpen.no/1106/RL791/3

Support

For issues with:

  • This MCP server: Open an issue in the repository
  • Planslurpen service: Visit https://planslurpen.no/ for contact information
  • MCP protocol: Refer to https://modelcontextprotocol.io/

Built with ❤️ for the Norwegian planning community

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选