bonsai-mcp
Related Servers
Alternatives to bonsai-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityCmaintenanceAn MCP server that connects AI language models with the Bonsai Blender add-on to read, create, and edit IFC models through high-level tool calls.63MIT
- AlicenseAqualityBmaintenanceAn 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.8MIT
- AlicenseAqualityBmaintenanceConnects MCP clients to a local Blender + Bonsai (BlenderBIM) session for scene inspection, IFC project querying, viewport screenshots, and executing Python code in Blender.87MIT
- AlicenseBqualityCmaintenanceAn MCP server that builds and modifies Blender .blend files, supporting both headless generation and live interaction with an open Blender window.16MIT
- AlicenseAqualityCmaintenanceA Model Context Protocol server that integrates Claude with Blender, enabling users to analyze and interact with IFC (Industry Foundation Classes) building models through natural language commands.1764MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that enables AI assistants like Codex or ChatGPT to inspect and control a local Blender scene, including creating objects, editing materials, setting cameras and lights, rendering previews, and saving safe copies of .blend files.MIT
TDQS
Scored across 28 tools
The bl_/ifc_ prefixes and read-vs-write verbs separate most tools cleanly, and each tool has a specific resource or action. A few adjacent reading tools and geometry-edit tools (e.g. ifc_model_info vs ifc_representation_stats, ifc_edit_profile vs ifc_set_extrusion_depth) could be confused, but their descriptions disambiguate them well.
All names are snake_case and consistently use bl_/ifc_ prefixes, which makes the set predictable. However, the verb convention is not uniform: mutation tools use verb_object patterns like ifc_set_attribute and ifc_move_element, while several read tools are noun-like (ifc_model_info, ifc_spatial_tree, ifc_geometry_info) rather than get_*.
At 28 tools, the set is above the 25-tool threshold where an agent's tool-selection burden becomes steep. Most tools are individually purposeful, but several read/reporting and viewport tools could plausibly be consolidated without losing capability.
The set covers a substantial IFC workflow: open, inspect, edit properties and pset values, transform geometry, save, validate, and revert. Notable gaps remain, however, including no creation or deletion of IFC elements, no material/type assignment tools, and no spatial-structure editing, so full modelling workflows are incomplete.