ifc-mcp
Enables AI agents to load, query, and analyze IFC building model files, including spatial structures, elements, properties, materials, and geometry.
README
IFC MCP Server
An MCP (Model Context Protocol) server that enables AI agents to understand and query IFC (Industry Foundation Classes) building model files. This server exposes a rich set of tools for loading IFC files, traversing spatial hierarchies, inspecting elements and properties, querying materials and quantities, and retrieving geometry bounding boxes — allowing AI assistants like Claude to reason about building information models without requiring the user to manually extract data.
Installation
From PyPI (recommended)
pip install ifc-mcp
# or with uv:
uv tool install ifc-mcp
Claude Desktop config (no path needed):
{
"mcpServers": {
"ifc": {
"command": "uvx",
"args": ["ifc-mcp"]
}
}
}
To update
uv tool upgrade ifc-mcp
Or pin to a specific version:
"args": ["ifc-mcp==0.2.0"]
Development Setup
Prerequisites: Python 3.11+, uv
git clone <repo>
cd IfcMcp
uv sync
uv run pytest # verify all tests pass
Claude Desktop config for local dev:
{
"mcpServers": {
"ifc": {
"command": "uv",
"args": ["run", "python", "server.py"],
"cwd": "/absolute/path/to/IfcMcp"
}
}
}
On Windows, use double backslashes: "cwd": "C:\\Users\\...\\IfcMcp"
Tools Reference
Every tool (except list_loaded_models) requires a model_id — the value returned by load_ifc_file.
| Tool | Parameters | Description |
|---|---|---|
load_ifc_file |
path |
Load an IFC file; returns model_id |
list_loaded_models |
— | List all models in memory |
unload_ifc_file |
model_id |
Free a loaded model |
get_spatial_structure |
model_id |
Full spatial hierarchy (Project→Site→Building→Storey→Space) |
get_element_containment |
model_id, global_id |
Spatial containment chain for an element |
get_elements_by_type |
model_id, ifc_type, limit, offset |
Paginated list by IFC type |
get_element_by_id |
model_id, global_id |
Full element details |
search_elements |
model_id, filters..., limit, offset |
Filter elements by type/name/pset/property |
get_property_sets |
model_id, global_id |
All Psets for an element |
get_quantities |
model_id, global_id |
All quantity sets for an element |
get_material |
model_id, global_id |
Material info (name, layers, category) |
get_model_statistics |
model_id |
Element counts by type, storey names, schema |
get_bounding_box |
model_id, global_id |
Min/max XYZ bounding box in project coordinates |
MCP Resource
Each loaded model exposes a pre-computed summary resource:
ifc://model/{model_id}/summary
This resource is computed at load time and contains the project name, IFC schema version, element counts by type, and storey names. It gives AI agents a fast overview of a model without issuing individual tool calls.
Error Responses
All tools return structured error objects. Common codes:
{"error": "element_not_found", "details": "..."}
{"error": "model_not_loaded", "details": "..."}
{"error": "geometry_unavailable", "details": "..."}
{"error": "file_not_found", "details": "..."}
{"error": "load_failed", "details": "..."}
{"error": "query_failed", "details": "..."}
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。