RhinoSAFE
RhinoMCP connects Rhino to Claude AI through the Model Context Protocol (MCP), enabling AI-assisted 3D modeling and architectural design.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
⚠️ UNDER CONSTRUCTION ⚠️ This project is currently under active development and is not yet in working order. The Rhino plugin is experiencing issues with creating objects. We are actively seeking support from the community to help resolve these issues. If you have experience with Rhino API development, C# plugins, or MCP integration, please consider contributing. Contact us by opening an issue on GitHub.
A Model Context Protocol (MCP) server implementation for Rhino 3D, allowing Claude to create and manipulate 3D objects.
Overview
This project implements an MCP server for Rhino 3D that enables AI assistants like Claude to interact with Rhino through the Model Context Protocol. The server allows for the creation and manipulation of 3D objects directly from the AI interface.
System Architecture
The system consists of Python components that implement the MCP server and C# components that integrate with Rhino. Here's an overview of how the system components interact:
graph TD %% Client Applications client[Client Applications] --> socketProxy %% Socket Proxy subgraph "Python Socket Proxy" socketProxy[socket_proxy.py] --> daemonServer end %% Daemon Server subgraph "Python Daemon Server" daemonServer[daemon_mcp_server.py] --> combinedServer end %% Combined MCP Server subgraph "Python Combined MCP Server" combinedServer[combined_mcp_server.py] mcp[FastMCP] --> tools combinedServer --> mcp combinedServer --> rhinoConn subgraph "MCP Tools" tools[MCP Tool Methods] end rhinoConn[RhinoConnection] end %% Rhino Plugin Components subgraph "C# Rhino Plugin" rhinoPlugin[RhinoMcpPlugin.cs] socketServer[RhinoSocketServer.cs] utilities[RhinoUtilities.cs] commands[RhinoMcpCommand.cs] rhinoPlugin --> socketServer rhinoPlu
9e5cf5ef9f56OBSERVED · 2026-10-08Exposed tools (7)
2 read · 4 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
clear_scene | destructive | |
create_box | write | |
create_cylinder | write | |
create_layer | write | |
create_sphere | write | |
get_scene_info | read | |
log_claude_message | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (6 observation(s))
- Network
- none-observed
- Shell
- declared (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (4)
clear_scene
load_dotenv() # load environment variables from .env
curl -LsSf https://astral.sh/uv/install.sh | sh
Gates applied: no_behavioural_pass, no_license.
9e5cf5ef9f56full audit observations/trust-audit/mcp-server/always-tinkering__rhino-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9e5cf5ef9f56 | SAFE | B | 89 | first audit |
Questions
What is the Rhino MCP server?
RhinoMCP connects Rhino to Claude AI through the Model Context Protocol (MCP), enabling AI-assisted 3D modeling and architectural design.
What tools does Rhino expose?
7 in total: 2 read-only, 4 that write, and 1 that can delete or overwrite (clear_scene). Every one is listed on this page with its risk.
Is Rhino safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Rhino 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 (9e5cf5ef9f56), read on 2026-10-08. The repository is watched and re-audited when it changes.