What is yade-mcp AGENTS.md?

Repository instructions for yade-mcp, an MCP server that connects AI agents to YADE, an open-source engine for simulating granular materials such as sand or powder. The project also includes a bridge that runs inside YADE, and it is organized as a monorepo containing both packages.

They guide building, linting, formatting, type-checking, testing, branching, and publishing the yade-mcp server and its YADE bridge.

They explain the two-package structure, required checks, branch rules, and release process. This helps agents test the right parts and avoid placing large files in the code branch.

How yusong652/yade-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to yusong652/yade-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/yusong652/yade-mcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/yusong652/yade-mcp

Made for: Codex, OpenCode.

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/yusong652/yade-mcp/agents-md.svg)](https://agentmods.dev/instructions/yusong652/yade-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/yusong652/yade-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/yusong652/yade-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 673 This file is loaded in full into every session.

When invoked 673 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00673	$0.00673
Opus 5	$0.00336	$0.00336
Sonnet 5	$0.00135	$0.00135
Haiku 4.5	$0.00067	$0.00067

Measured 6d ago against content hash df5aaa9f7f6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

yade-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 6d 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.

AGENTS.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project overview

yade-mcp is an MCP server that connects AI agents to YADE (open-source DEM engine). Two packages live in this monorepo:

yade-mcp (src/yade_mcp/) — MCP server with 7 tools (2 doc + 5 execution)
yade-mcp-bridge (yade-mcp-bridge/) — WebSocket bridge running inside YADE process

Build and test

uv sync --group dev                    # install dependencies
uv run ruff check src/                 # lint MCP server
uv run ruff check yade-mcp-bridge/src/ # lint bridge (uses bridge's own ruff config)
uv run ruff format src/                # format
uv run mypy src/yade_mcp/              # type check
uv run pytest tests/ -v --ignore=tests/test_tools_integration.py  # unit + protocol tests (no YADE needed)
uv run pytest tests/ -v                # all tests (integration tests need YADE + bridge)

Branch strategy

master — code only, kept lightweight
assets — large binary files (header.gif, header.blend, generation scripts)

Do NOT commit large files (images, .blend, etc.) to master.

Release workflow

Tag-based via GitHub Actions:

v* tags → publish yade-mcp to PyPI (e.g., git tag -a v0.1.3 -m "...")
bridge-v* tags → publish yade-mcp-bridge to PyPI (e.g., git tag -a bridge-v0.1.1 -m "...")

Both use trusted publishing (PyPI OIDC). Version is defined in __init__.py of each package.

Coding conventions

Ruff for linting and formatting (N818: exception names must end with Error)
Bridge has its own ruff config in yade-mcp-bridge/pyproject.toml (targets py38, ignores UP032/SIM115)
Async-first: bridge client uses websockets with asyncio
Response envelope: all tools return via build_ok() / build_error() from contracts.py

Test structure

tests/ — MCP server unit tests (config, contracts, formatting, search, response truncation)
tests/bridge/ — Bridge unit + protocol tests (no YADE runtime needed)
- test_helpers.py, test_signals.py, test_utils.py, test_execution.py, test_tasks.py — unit tests
- test_handlers.py — handler tests with mock context
- test_protocol.py — real WebSocket server, tests message format and routing
tests/test_bridge_client.py — MCP bridge client (needs running bridge)
tests/test_tools_integration.py — end-to-end MCP tools (needs YADE + bridge)

Read the full file on GitHub · 58 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.

6d ago First seen · 58 lines · 673 tokens per session scan A df5aaa9f7f6f

Subscribe to this mod's changes

yade-mcp AGENTS.md is an instructions file published in the GitHub repository yusong652/yade-mcp (13 stars, last pushed 8d ago), licensed MIT. It adds 673 tokens to every session, about $0.0034 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 2026-08-30.

Building agents Scientific ai anthropic claude dem discrete-element-method geomechanics

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 · 5,182 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

yade-mcp: Instructions file for Codex