Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/simliverse/simliverse-mcp/agents-mdgit clone --depth 1 https://github.com/SimLiverse/simliverse-mcpWrote 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.
[](https://agentmods.dev/instructions/simliverse/simliverse-mcp/agents-md)<a href="https://agentmods.dev/instructions/simliverse/simliverse-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/simliverse/simliverse-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01323 | $0.01323 |
| Opus 5 | $0.00661 | $0.00661 |
| Sonnet 5 | $0.00265 | $0.00265 |
| Haiku 4.5 | $0.00132 | $0.00132 |
Grade A, and why
simliverse-mcp AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents (and humans) working in this repository.
What this repo is
simliverse-mcp is an experimental Model Context Protocol (MCP) server that exposes NVIDIA
Isaac Sim as a set of tool-callable actions (scene setup, robot/object creation, sensors,
lighting, materials, action graphs, simulation stepping, etc.). The tool implementations live
in isaac_mcp/tools/, the MCP entry point is isaac_mcp/server.py, the transport/connection
layer is isaac_mcp/connection.py, and the Isaac Sim-side extension that the server talks to
is isaac.sim.mcp_extension/.
This repo is currently under experiment. It is not a finished, stable product. The longer-term goal is an AI agent for SimLiverse that includes a sub-agent for managing Isaac Sim; this repo is the test bed for building the Isaac Sim MCP server half of that. Expect churn in tool names, arguments, and behavior.
Relationship to upstream and to simliverse-core
- This repo is a fork of the external upstream project
whats2000/isaacsim-mcp-server. General contribution norms (dev environment setup, PR process, code style, project layout) are inherited from that upstream project — see CONTRIBUTING.md for those details rather than duplicating them here. - This server is consumed by simliverse-core, specifically
api/app/services/mcp_bridge.py, which resolves the private VPC IP of a job's worker VM and talks to this server's/mcpendpoint using MCP JSON-RPC 2.0. The integration is documented (as of this writing) insimliverse-core/docs/adr/010-isaacsim-copilot-mcp-bridge.md(relative path in the siblingsimliverse-corerepo — not guaranteed to be readable from here, check if it exists before relying on it). - The agent harness in simliverse-core that drives this MCP server currently doesn't work
well at all. simliverse-core's own
ARCHITECTURE.md(§9) explicitly flags that "the MCP tool-call contract between this bridge and simliverse-mcp is unstable" and recommends investigating that contract before expanding further. Anyone picking up work here should expect to dig into that integration rather than assume it's solid.
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.
- 4d ago First seen · 87 lines · 1,323 tokens per session scan A cf7c540b1c63
simliverse-mcp AGENTS.md is an instructions file published in the GitHub repository SimLiverse/simliverse-mcp (0 stars, last pushed today), licensed MIT. It adds 1,323 tokens to every session, about $0.0066 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
cml-mcp AGENTS.md
AGENTS.md instructions for xorrkaz/cml-mcp, covering agents.md — cml mcp server, project overview, compatibility goal, repository layout and tool modules (src/cmlmcp/tools/).
brilliant_sdk AGENTS.md
Instructions for brilliantlabsAR/brilliant_sdk, covering brilliant sdk — agent guide, how an app works (the pattern behind everything), minimal reading paths, verify without hardware and testing.
NeoMind CLAUDE.md
Claude Code instructions for camthink-ai/NeoMind, covering neomind — edge ai platform for iot, development commands, ecosystem repositories, extension package contract (.nep) and device type template contract (json).
cad-cae-copilot copilot-instructions.md
Copilot instructions for armpro24-blip/cad-cae-copilot, covering github copilot — aieng workspace and essentials.
phone-mcp CLAUDE.md
Claude Code instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.
zmk-config AGENTS.md
AGENTS.md instructions for urob/zmk-config, covering customization guide, ground rules, how the multi-board layout works, adding a new board and where to change what.