ArchiCAD
This MCP server implementation by Luka Gradisar provides AI assistants with direct access to ArchiCAD's API functionality through the Tapir command system. Built with Python using FastMCP and the official ArchiCAD Python library, it dynamically registers all available Tapir commands from ArchiCAD's command definitions and schema files, automatically handling input validation and parameter resolution. The implementation parses JavaScript-based command definitions to create properly typed MCP tools, enabling AI models to perform architectural modeling operations, element manipulation, and project management tasks within ArchiCAD. It serves architects and designers who want to integrate AI assistance into their CAD workflows, allowing for automated building design tasks, parametric modeling operations, and project analysis through conversational interfaces.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- productivity
- Source
- PulseMCP
- Repository
- github.com/lgradisar/archicad-mcp
- Author type
- human
- Updated
- 2026-04-25
Use via MCP
Resolve ArchiCAD from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.