Skip to main content

ifc-mcp

MCP server for exploring and querying IFC (Industry Foundation Classes) building models.

Install

pip install ifc-mcp

ifc-mcp must be on your PATH for MCP clients that use command: "ifc-mcp".

which ifc-mcp
ifc-mcp --help
ifc-mcp --version

Run

Start once and load models dynamically during chat:

ifc-mcp serve

Optional preload:

ifc-mcp serve /absolute/path/to/model.ifc

HTTP transport:

ifc-mcp serve --transport http --port 8000

MCP client config

{
  "mcpServers": {
    "ifc_mcp": {
      "command": "ifc-mcp",
      "args": ["serve"]
    }
  }
}

Typical workflow in chat

  1. load_model(file_path="/absolute/path/to/model.ifc") (fast default)
  2. get_model_summary()
  3. Query with tools by element, space, material, property, or type.

Most tools also accept optional file_path for one-shot queries.

Geometry is loaded lazily by default for speed. Use eager mode only when needed:

  • MCP tool: load_model(file_path="...", with_geometry=true)
  • CLI preload: ifc-mcp serve /absolute/path/to/model.ifc --with-geometry
  • Session status: get_loaded_model() includes geometry_loaded

Relationship tools

ifc-mcp includes element relationship tools based on IfcRelContainedInSpatialStructure and IfcRelAggregates:

  • classify_elements_by_relation(file_path="/absolute/path/to/model.ifc") returns parent, child, and investigate buckets for IfcElement records.
  • get_aggregate_relationships(file_path="/absolute/path/to/model.ifc") returns aggregate parents, their children, and a flat child_to_parent map.
  • find_orphans(file_path="/absolute/path/to/model.ifc", exclude_classes=["IfcOpeningElement"]) returns elements with neither spatial containment nor aggregate parent links.

License

MIT

Metadata

Release files for ifc-mcp 0.2.7

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ifc-mcp 0.2.7
File Size Uploaded Provenance Actions
ifc_mcp-0.2.7.tar.gz 19.4 MB Without provenance Details for ifc_mcp-0.2.7.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ifc-mcp 0.2.7
File Interpreter ABI Platform Actions
ifc_mcp-0.2.7-py3-none-any.whl Python 3 none any Details for ifc_mcp-0.2.7-py3-none-any.whl

Total release size: 19.4 MB

Release files / ifc_mcp-0.2.7.tar.gz

Download URL ifc_mcp-0.2.7.tar.gz
Size 19.4 MB
Tags Source
SHA-256 checksum
How to use checksums
6e3687b4c8bbce84e7f4beb8f8b3f317788e7bcaf3a3047a1ec36a1740d49cb1
BLAKE2b-256 checksum
How to use checksums
eed274ee73e4c3d978dca435fe7c83dba0abd9948123de23ac669d127325ea0c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5

Release files / ifc_mcp-0.2.7-py3-none-any.whl

Download URL ifc_mcp-0.2.7-py3-none-any.whl
Size 69.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c0da90ee240798b82ef34837559c9939bcbe92a8b4b43d92e0681bf676600466
BLAKE2b-256 checksum
How to use checksums
f5b266f0d0cf180de12c1ce8a5fcb9820fd654812057c1ce88216ec7f72fb901
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5

Security for ifc-mcp 0.2.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page