How do I install the Bonsai MCP skill?

Run npx skillmds@latest add autonomous-ai/bonsai-mcp in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Bonsai MCP safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Bonsai MCP?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Bonsai MCP free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Bonsai MCP?

autonomous-ai (@autonomous-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Bonsai MCP by autonomous-ai — Agent Skill

Name: Bonsai MCP
Author: autonomous-ai

File contents

House of ideas

Read studio.json to understand the current controls; "$STUDIO_TOOLCHAIN/../studio.config.json" describes their ranges. Run "$STUDIO_TOOLCHAIN/run.sh" build to make a new result. Successful artifacts and their measurements are in out/runs/<id>/; out/latest.json names the current result. A failed run preserves the last success and records the error in the verdict.

The local workflow creates and reopens a real IFC4 building with IfcOpenShell, including storeys, slabs, walls, spaces and quantities. The in-pane drawing is a schematic model inspector. It does not certify structural adequacy or code compliance. Blender/Bonsai editing remains available through the pinned optional bridge.

Use "$STUDIO_TOOLCHAIN/../README.md" for the integration contract and commands. Read the relevant files under $STUDIO_UPSTREAM before using an upstream API. Keep controls within their documented ranges, preserve the data needed to reproduce a comparison, and distinguish preview results from native service or hardware output. The viewer supports history and artifact downloads; tell the user which run contains the result, and what was actually measured.

Author and check building data

Choose the footprint, storeys, height, and room use, then run build. Reopen building.ifc with IfcOpenShell, inspect spaces/walls/openings, and read the quantity sets. Match their areas and volumes to quantities.csv. The canvas is a schematic view; IFC is the source artifact for downstream editing. Preserve element identifiers when extending an existing model.

Read $STUDIO_UPSTREAM/docs/examples.md for Bonsai edits and read-back verification, docs/installation.md for the bridge, and docs/tools.md before native commands. The wrapper's bonsai action only requests scene information from an existing Blender session.

---name: bonsai-mcpdescription: Create and inspect architecture projects in the Bonsai MCP Harness workspace, including its local starter and optional upstream integration.---# House of ideasRead `studio.json` to understand the current controls; `"$STUDIO_TOOLCHAIN/../studio.config.json"`describes their ranges. Run `"$STUDIO_TOOLCHAIN/run.sh" build` to make a new result.Successful artifacts and their measurements are in `out/runs/<id>/`; `out/latest.json` names thecurrent result. A failed run preserves the last success and records the error in the verdict.The local workflow creates and reopens a real IFC4 building with IfcOpenShell, including storeys, slabs, walls, spaces and quantities. The in-pane drawing is a schematic model inspector. It does not certify structural adequacy or code compliance. Blender/Bonsai editing remains available through the pinned optional bridge.Use `"$STUDIO_TOOLCHAIN/../README.md"` for the integration contract and commands. Read the relevantfiles under `$STUDIO_UPSTREAM` before using an upstream API. Keep controls within their documentedranges, preserve the data needed to reproduce a comparison, and distinguish preview results fromnative service or hardware output. The viewer supports history and artifact downloads; tell theuser which run contains the result, and what was actually measured.## Author and check building dataChoose the footprint, storeys, height, and room use, then run `build`. Reopen `building.ifc`with IfcOpenShell, inspect spaces/walls/openings, and read the quantity sets. Match theirareas and volumes to `quantities.csv`. The canvas is a schematic view; IFC is the sourceartifact for downstream editing. Preserve element identifiers when extending an existing model.Read `$STUDIO_UPSTREAM/docs/examples.md` for Bonsai edits and read-back verification,`docs/installation.md` for the bridge, and `docs/tools.md` before native commands. Thewrapper's `bonsai` action only requests scene information from an existing Blender session.

Frequently asked questions

Bonsai MCP