Skip to main content
Glama
ifc-sql-mcp

ifc-sql-mcp

ifc-sql-mcp

CI

Load IFC files exported from Autodesk Revit into a normalised PostgreSQL database and expose the data to LLMs through an MCP server.

Status: under active development. This README is a placeholder until the pipeline is complete; the full write-up (architecture, data model, data-quality findings, MCP tools) will replace it.

Development

Requires uv and Docker.

make up        # start PostgreSQL 16 (docker compose) and wait until it is healthy
make migrate   # create the ifc schema: tables, views and the read-only role
make test      # unit + integration tests with coverage (needs `make up`)
make lint      # ruff lint + format check
make help      # every target

Download the pinned, checksum-verified sample models (not stored in this repo):

make samples   # or: uv run python scripts/download_samples.py arc

The schema is described in docs/data-model.md; design decisions are recorded in docs/adr/.

Related MCP server: Horizun Revit MCP

Licences

Code: MIT. Sample data: CC BY 4.0, see DATA_ATTRIBUTION.md.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Enables AI agents to load, query, and analyze IFC building model files, including spatial structures, elements, properties, materials, and geometry.
      20
      1
      MIT
    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      Connects MCP clients like Claude, Codex, and Cursor to a running Autodesk Revit session for typed BIM queries, verified model edits, family authoring, exports, and Power BI workflows. It is open-source, Apache-2.0, and designed for reliable, verified outcomes.
      -
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that lets users query, validate, convert, and compare IFC/BIM files using natural language. Runs fully locally and integrates with AI agents like Claude.
      8
      MIT