Atlas / MCP servers / jotaderodriguez / Bonsai

BonsaiBLOCK

mcp/jotaderodriguez/bonsai
Verdict
BLOCK
Grade
D
Trust score
69 /100
Exposed tools
15 14r · 1w · 0d
Transport
—
License
MIT
Stars
64
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Bonsai-mcp is a fork of BlenderMCP that extends the original functionality with dedicated support for IFC (Industry Foundation Classes) models through Bonsai. This integration is a platform to let LLMs read and modify IFC files.

Features

  • IFC-specific functionality: Query IFC models, analyze spatial structures, examine building elements and extract quantities
  • Eleven IFC tools included: Inspect project info, list entities, examine properties, explore spatial structure, analyze relationships and more
  • Execute Code tool from the original BlenderMCP implementation: Create and modify objects, apply materials, and execute Python code in Blender

Components

The system consists of two main components:

  1. Blender Addon (`addon.py`): A Blender addon that creates a socket server within Blender to receive and execute commands, including IFC-specific operations
  1. MCP Server (`tools.py`): A Python server that implements the Model Context Protocol and connects to the Blender addon

Installation - Through MCP Client Settings

Prerequisites

  • Blender 4.0 or newer
  • Python 3.12 or newer
  • uv package manager
  • Bonsai BIM addon for Blender (for IFC functionality)

Installing uv:

Mac:


brew  install  uv

Windows:


powershell  -c  "irm https://astral.sh/uv/install.ps1 | iex"

set  Path=C:\Users\[username]\.local\bin;%Path%

For other platforms, see the uv installation guide.

Clone the repository


git  clone  https://github.com/JotaDeRodriguez/Bonsai_mcp

Claude for Desktop In

Read from source at commit 8c295899e692OBSERVED · 2026-10-08
Advertisement
02

Connect

Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.

claude-code
claude mcp add Bonsai_mcp -- uvx Bonsai_mcp
claude-desktop
{
  "mcpServers": {
    "Bonsai_mcp": {
      "command": "uvx",
      "args": [
        "Bonsai_mcp"
      ]
    }
  }
}
03

Exposed tools (15)

14 read · 1 write · 0 destructive.

ToolRiskDescription
execute_blender_codewrite
export_bc3_budgetread
export_drawing_pngreadExport drawings as PNG images with custom resolution.
export_ifc_dataread
get_ifc_georeferencing_inforead
get_ifc_project_inforead
get_ifc_propertiesread
get_ifc_quantitiesread
get_ifc_relationshipsread
get_ifc_spatial_structureread
get_ifc_total_structureread
get_selected_ifc_entitiesread
get_user_viewread
list_ifc_entitiesread
place_ifc_objectread
04

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (1 observation(s))
Network
none-observed
Shell
declared (1 observation(s))
Dependencies
pinned
Secrets in source
none-found

Findings (3)

HIGHCode injection · code.eval_exec · CWE-78, CWE-94, CWE-95
addon.py:262
exec(code, namespace)
Why it matters. evaluates text as code
Fix. remove; use a parser or a dispatch table
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tools.py:567
image_data = base64.b64decode(result["data"])
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tools.py:794
image_data = base64.b64decode(result["data"])

Gates applied: no_behavioural_pass.

Audited 2026-10-08 · audit v0.4.1 · source sha 8c295899e692full audit observations/trust-audit/mcp-server/jotaderodriguez__bonsai.json · Report an issue / request a re-scan
05

Audit history

Every audit this server has had. A grade with a past is a grade somebody is still checking.

DateSourceVerdictGradeScoreChange
2026-10-088c295899e692BLOCKD69first audit
06

Questions

What tools does Bonsai expose?

15 in total: 14 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is Bonsai safe to connect to an agent?

No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.

What credentials does Bonsai need?

No credential environment variables were found in its source, so it appears to need none.

How current is this page?

The grade is for one exact copy of the source (8c295899e692), read on 2026-10-08. The repository is watched and re-audited when it changes.

Advertisement