What is rhino-mcp CLAUDE.md?

Repository instructions for an MCP server that lets an AI model control Rhino 8, a 3D architectural modelling application. They describe its Python server, C# plugin, connection setup, commands, and checks for whether generated geometry matches the intended design.

Use them when developing or maintaining the Rhino integration, running its self-test, changing its Python or .NET components, or adding checks for geometry, dimensions, and unsupported operations.

They give coding agents the project-specific setup and safety rules needed to work on the server. They also address a key modelling problem: geometry can be technically valid while still being the wrong shape or size.

How tanishqbhattad/rhino-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to tanishqbhattad/rhino-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tanishqbhattad/rhino-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/tanishqbhattad/rhino-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/tanishqbhattad/rhino-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/tanishqbhattad/rhino-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/tanishqbhattad/rhino-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tanishqbhattad/rhino-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/tanishqbhattad/rhino-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/tanishqbhattad/rhino-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,836 This file is loaded in full into every session.

When invoked 1,836 The same file — it is already loaded in full.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01836	$0.01836
Opus 5.5	$0.00734	$0.00734
Sonnet 5.5	$0.00367	$0.00367
Haiku 4.5	$0.00184	$0.00184

Measured 24d ago against content hash 2a8cd3092c93, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

rhino-mcp CLAUDE.md scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 24d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Tells the agent never to refusehighAnti-refusal

Suppressing the ability to decline removes a core safety control; a later harmful request then succeeds.

exactly as before (never refuse). One that claimed it and then failed is refused. Both

CLAUDE.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — rhino-mcp

Guidance for Claude Code working in this repository. Full engineering handoff: docs/HANDOFF.md — read it first in a new session.

What this is

An MCP server giving an LLM control of Rhino 8 for architectural modelling. Two processes:

server/ — Python FastMCP server (128 tools), talks MCP/stdio to the client
plugin/ — C# .NET 8 RhinoCommon plugin (.rhp) running inside Rhino
They speak Protocol 5.1 over TCP 127.0.0.1:9544 (override: RHINO_HOST/RHINO_PORT)

Nothing works without Rhino 8 open and the AIBridge plugin loaded. Without it every tool times out. run_selftest (~700 ms warm, six stages) is the fastest way to confirm the stack is alive.

Core design principle

Valid geometry ≠ correct geometry. An LLM building thousands of parametric objects makes arithmetic and wiring errors that produce perfectly valid breps. So this server validates intent: assert_geometry, assert_dimensions, find_unsupported, section_preview. New features should be able to tell the model it built the wrong thing — not just that it parsed.

Commands

# Python
uv --directory server sync --group dev --frozen
uv --directory server run python -m pytest -q          # 143 collected
# If uv can't reinstall because a running MCP server holds rhino-architect.exe open
# (happens after a version bump), add --no-sync - the install is editable anyway.
uv --directory server run ruff check src tests ../evals
uv --directory server run rhino-architect-doctor

# C# plugin  — CLOSE RHINO FIRST (it holds the .rhp open)
cd plugin ; .\build.bat

# Evals (semi-automated: the agent half runs in the MCP client)
uv --directory server run python ../evals/run_evals.py list
uv --directory server run python ../evals/run_evals.py check gothic_cathedral --label opus-5

# Session distiller: mine the WAL for skill/eval material (report needs no Rhino)
uv --directory server run python ../evals/distill_session.py report latest

Read the full file on GitHub · 124 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

24d ago First seen · 124 lines · 1,836 tokens per session scan C 2a8cd3092c93

Subscribe to this mod's changes

rhino-mcp CLAUDE.md is an instructions file published in the GitHub repository tanishqbhattad/rhino-mcp (34 stars, last pushed 25d ago), licensed MIT. It adds 1,836 tokens to every session, about $0.0073 per session on Opus 5.5. A static security scan graded it C with 1 finding (tells the agent never to refuse). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.

Building agents Design and UX ai architecture artificial-intelligence bim chatgpt claude

rhino-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
rhino-mcp CLAUDE.mdtanishqbhattad/rhino-mcp	Instructions file	34	25d ago	MIT	C	1,836	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

rhino-mcp: Instructions file for Claude Code