IFC Building Information Modeling MCP server

ifcMCP is a server that allows Large Language Model (LLM) agents to interact with IFC (Industry Foundation Classes) files. This enables AI assistants to understand and manipulate building information models through natural language, making BIM data more accessible and useful in conversational AI contexts.

Installation

To set up the ifcMCP server:

1. Clone the repository:

   git clone https://github.com/smartaec/ifcMCP.git
   

2. Install the required packages:

   • ifcopenshell
   • FastMCP

   You can install these using pip:

   pip install ifcopenshell FastMCP
   

3. Start the server:

   cd ifcMCP
   python server.py
   

Using ifcMCP

Configuring Your LLM Tool

After starting the server, you need to configure your LLM tool to connect to the MCP server:

1. Open your preferred LLM tool that supports MCP
2. Add the following configuration:

   {
     "mcpServers": {
       "ifcMCP-server": {
         "name": "ifcMCP",
         "type": "streamableHttp",
         "description": "A simple MCP server to handle ifc files",
         "isActive": true,
         "tags": [],
         "baseUrl": "http://127.0.0.1:8000/mcp"
       }
     }
   }
   

Supported Tools

The ifcMCP server supports various operations on IFC files:

• get_entities: Retrieve entities from the IFC model
• get_named_property_of_entities: Get specific named properties of entities
• get_entity_properties: Retrieve all properties of a specific entity
• get_entity_location: Get the spatial location of an entity
• get_entities_in_spatial: Find entities within a spatial structure
• get_openings_on_wall: Identify openings in walls
• get_space_boundaries: Retrieve space boundary information

Example Usage

Once connected, you can instruct your LLM to interact with IFC files using natural language. For example:

• "Show me all the walls in this building model"
• "What are the properties of this door?"
• "Find all spaces on the second floor"
• "What are the dimensions of this room?"

The LLM will use the appropriate ifcMCP tools to extract the requested information from the IFC file and present it to you.

Troubleshooting

If you encounter connection issues:

• Ensure the server is running at http://127.0.0.1:8000
• Check that your LLM tool supports the MCP protocol
• Verify that the configuration JSON is correctly formatted

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ifcMCP-server" '{"name":"ifcMCP","type":"streamableHttp","description":"A simple MCP server to handle ifc files","isActive":true,"tags":[],"baseUrl":"http://127.0.0.1:8000/mcp"}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ifcMCP-server": {
            "name": "ifcMCP",
            "type": "streamableHttp",
            "description": "A simple MCP server to handle ifc files",
            "isActive": true,
            "tags": [],
            "baseUrl": "http://127.0.0.1:8000/mcp"
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ifcMCP-server": {
            "name": "ifcMCP",
            "type": "streamableHttp",
            "description": "A simple MCP server to handle ifc files",
            "isActive": true,
            "tags": [],
            "baseUrl": "http://127.0.0.1:8000/mcp"
        }
    }
}

3. Restart Claude Desktop for the changes to take effect