What is reachy-mini-mcp CLAUDE.md?

Repository instructions for an AI coding assistant working on an MCP server that connects AI tools to a Reachy Mini robot's REST service. REST is a web interface for reading data and triggering actions.

Understanding the Python server, Docker distribution, standard-input communication, robot telemetry, motion commands, and how to resolve conflicts with the canonical specifications.

They describe the authoritative specifications, architecture, and startup expectations so implementation follows the intended robot behavior.

How nolte/reachy-mini-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nolte/reachy-mini-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/nolte/reachy-mini-mcp/develop/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nolte/reachy-mini-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/nolte/reachy-mini-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/nolte/reachy-mini-mcp/claude-md)

Your own site

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

Per session 864 This file is loaded in full into every session.

When invoked 864 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 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	$0.00864	$0.00864
Opus 5.5	$0.00346	$0.00346
Sonnet 5.5	$0.00173	$0.00173
Haiku 4.5	$0.00086	$0.00086

Measured 2mo ago against content hash 36f12524b107, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

reachy-mini-mcp 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 2mo 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 · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

AI-collaboration conventions, architecture hints, and command entry points for the reachy-mini-mcp repository.

What this repo is

A Model Context Protocol (MCP) server that wraps the Pollen reachy-mini daemon's REST surface so MCP-capable LLM frontends (Claude Desktop, Claude Code, Cursor) can read robot telemetry and trigger motion. Distribution form is a Docker container with stdio transport.

Canonical specifications

This repository implements specs that live elsewhere; do not redefine them here.

claude-reachy-mini/spec/reachy-mini/mcp-server/de.md — canonical product spec for this MCP server (German is canonical; en.md is the translation kept in sync).
claude-reachy-mini/spec/claude/mcp-server-bootstrap/de.md — operational bootstrap spec describing host/daemon expectations.
claude-shared/spec/project/project-structure/de.md — repository layout this repo follows.

When the implementation and the specs disagree, the spec wins. Open a PR against the spec repo before silently diverging here.

Architecture at a glance

Python 3.12, single-purpose layout: source under src/reachy_mini_mcp/.
Transport: stdio MCP; the server is launched as python -m reachy_mini_mcp.
Outbound: httpx against the Pollen daemon at REACHY_MINI_DAEMON_URL (default http://127.0.0.1:8000, never a non-localhost address by default per spec).
Audit log: per-invocation JSONL under ${XDG_CACHE_HOME}/reachy-mini-mcp/.
Tiered tool surface (per spec): Tier 1 read-only, Tier 2 motion-safe, Tier 3 motion-active. Current state is skeleton — only health_check exists.

Dependency layout

Runtime dependencies live in requirements.txt (not in pyproject.toml's [project.dependencies], per the project-structure spec).
Development / test dependencies live in requirements-dev.txt. The -r requirements.txt chaining directive is forbidden by spec — install both files independently.
pyproject.toml carries distribution metadata (name, version, authors, urls) and tooling config ([tool.ruff], [tool.pytest.ini_options]) only.

Read the full file on GitHub · 60 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.

2mo ago First seen · 60 lines · 864 tokens per session scan A 36f12524b107

Subscribe to this mod's changes

reachy-mini-mcp CLAUDE.md is an instructions file published in the GitHub repository nolte/reachy-mini-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 864 tokens to every session, about $0.0035 per session on Opus 5.5. 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.

mcp model-context-protocol reachy-mini

reachy-mini-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
reachy-mini-mcp CLAUDE.mdnolte/reachy-mini-mcp	Instructions file	0	1mo ago	MIT	A	864	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	yesterday	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

reachy-mini-mcp: Instructions file for Claude Code