isaacsim-mcp-server: Instructions file for Claude Code

CLAUDE.md

isaacsim-mcp-server CLAUDE.md is an instructions file for Claude Code from whats2000/isaacsim-mcp-server. It costs 3,594 tokens per session, scanned A, original, from a forked repository, MIT.

Project-specific instructions for an MCP server that connects software to Isaac Sim, a robotics and physics simulator.

In plain words
What is it for?
Developing, testing, and extending the Isaac Sim MCP server and its simulator integration.
Why use it?
They document repository commands, testing requirements, and conventions for working safely on the project.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is whats2000/isaacsim-mcp-server's own configuration. It tells Claude Code how to work on isaacsim-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything isaacsim-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to whats2000/isaacsim-mcp-server. 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/whats2000/isaacsim-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/whats2000/isaacsim-mcp-server

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.

agentmods badge for isaacsim-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/whats2000/isaacsim-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/whats2000/isaacsim-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/whats2000/isaacsim-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/whats2000/isaacsim-mcp-server/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.

agentmods 80×15 button for isaacsim-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/whats2000/isaacsim-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/whats2000/isaacsim-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,594 This file is loaded in full into every session.
When invoked 3,594 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin fork From a forked repository.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.03594 $0.03594
Opus 5 $0.01797 $0.01797
Sonnet 5 $0.00719 $0.00719
Haiku 4.5 $0.00359 $0.00359

Measured 4d ago against content hash 0029b9241d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

isaacsim-mcp-server CLAUDE.md scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Commands

uv sync                              # install deps (creates .venv)
uv run pre-commit install            # ruff lint+format on commit
uv run pytest                        # unit suite only; live tests skip unless opted in
ISAAC_MCP_LIVE_TESTS=1 uv run pytest # ALSO runs tests that MUTATE a running Isaac Sim
uv run pytest tests/test_adapter_v6.py::test_get_adapter_returns_v6_when_version_6   # single test
uv run ruff check . && uv run ruff format .                                 # what CI enforces
uv run python add_license_headers.py # prepend the MIT header to new .py files

Live testing (unit tests alone are not sufficient — CONTRIBUTING requires verifying in a running simulator, and stating the Isaac Sim version in the PR):

./scripts/run_isaac_sim.sh              # Kit + extension; --newton / --physx / ISAACSIM_ENGINE
./scripts/dev_mcp_server.sh             # MCP server + extension hot-reload watcher
python scripts/smoke_test.py            # one socket command per surface, pass/fail per check
python scripts/smoke_test.py --port 8767   # a second instance (e.g. 5.1 alongside 6.0)
./.venv/bin/python -m mcp dev ./isaac_mcp/server.py   # MCP inspector on :5173

dev_mcp_server.sh reloads handler/adapter modules inside the running Kit process, so extension edits do not need an Isaac Sim restart. MCP-server-side edits (isaac_mcp/) do need the MCP client to restart the server.

Architecture

Two processes, one JSON-over-TCP hop (localhost:8766, ISAAC_MCP_PORT to change):

MCP client → isaac_mcp/ (FastMCP, stdio) → socket → isaac.sim.mcp_extension/ (Omniverse ext) → adapter → Isaac Sim APIs

MCP sideisaac_mcp/server.py builds FastMCP, attaches the _INSTRUCTIONS block (the agent-facing contract doc: workflow, debug loop, silent-failure map), and calls register_all_tools. Each module in isaac_mcp/tools/ exposes register_tools(mcp, get_connection); every tool serializes params, calls conn.send_command("<category>.<verb>", params), and returns json.dumps(result). Tools never raise — errors come back as {"status": "error", "message": ...} JSON strings.

Read the full file on GitHub · 119 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.

  1. 4d ago Changed · +13 lines · +352 tokens per session 0029b9241d4f
  2. 5d ago First seen · 106 lines · 3,242 tokens per session scan A 77c01fe4bc90

Subscribe to this mod's changes

isaacsim-mcp-server CLAUDE.md is an instructions file published in the GitHub repository whats2000/isaacsim-mcp-server (64 stars, last pushed 5d ago), licensed MIT. It adds 3,594 tokens to every session, about $0.0180 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens