What is mavlink-mcp CLAUDE.md?

Instructions for a server that lets AI assistants communicate with drones through MAVLink, a common drone communication protocol. It uses MAVSDK to support PX4, ArduPilot, and Pixhawk-class systems, with safety controls such as read-only mode, altitude limits, and a soft geofence.

Use them when developing or maintaining the MAVLink MCP server, its drone capabilities, adapters, safety guardrails, scripts, or MCP tools.

They explain the server's boundaries and architecture so changes do not bypass its safety checks or protocol separation. This matters when software can interact with physical aircraft.

How hieutachi/mavlink-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to hieutachi/mavlink-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/hieutachi/mavlink-mcp/main/CLAUDE.md

Clone the repo

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

Your own site

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

Per session 757 This file is loaded in full into every session.

When invoked 757 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	$0.00757	$0.00757
Opus 5	$0.00378	$0.00378
Sonnet 5	$0.00151	$0.00151
Haiku 4.5	$0.00076	$0.00076

Measured 10d ago against content hash 302967ba25c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mavlink-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 10d 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 · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guidance for Claude Code when working in this repository.

What this is

mavlink-mcp is a vendor-neutral UAV capability layer plus an MCP server. AI agents talk to MAVLink drones (PX4/ArduPilot SITL or Pixhawk-class hardware) through MAVSDK (BSD-3). It is the sister of rosbridge-mcp.

Do not rename the Python package (mavlink_mcp) or the console script (mavlink-mcp).

Architecture

AI client (MCP stdio)
  -> mavlink_mcp.server (FastMCP tools)
    -> mavlink_mcp.Drone          # owns all policy
      -> DroneAdapter             # protocol-agnostic interface
        -> MavsdkAdapter          # only module that imports mavsdk
          -> MAVLink UDP (default udpin://0.0.0.0:14540)

src/mavlink_mcp/capabilities.py — physical-quantity types (degrees, meters, volts); no protocol messages.
src/mavlink_mcp/drone.py — capability checks + guardrails.
src/mavlink_mcp/guardrails.py — readonly (default on), altitude ceiling, soft geofence.
src/mavlink_mcp/adapters/mavsdk_adapter.py — MAVSDK translation only.
src/mavlink_mcp/server.py — 12 MCP tools over 8 capabilities.

Python scripts use Drone directly; MCP clients use the mavlink-mcp console script. Same policy either way.

Commands

pip install -e ".[dev]"
pytest                          # mock adapter; no SITL required
mavlink-mcp                     # stdio MCP server

SITL (optional, see docs/simulator-quickstart.md):

docker run --rm -it jonasvautherin/px4-gazebo-headless:1.14.3

Environment

Variable	Default	Meaning
`MAVLINK_MCP_URL`	`udpin://0.0.0.0:14540`	MAVLink endpoint
`MAVLINK_MCP_READONLY`	`true`	Rejects every tool that can move the vehicle
`MAVLINK_MCP_MAX_ALTITUDE_M`	`50`	Relative altitude ceiling; `0` disables
`MAVLINK_MCP_GEOFENCE_RADIUS_M`	`200`	Soft geofence around home; `0` disables

Arm and takeoff also require confirm=true even when readonly is off.

Read the full file on GitHub · 63 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.

10d ago First seen · 63 lines · 757 tokens per session scan A 302967ba25c7

Subscribe to this mod's changes

mavlink-mcp CLAUDE.md is an instructions file published in the GitHub repository hieutachi/mavlink-mcp (2 stars, last pushed 23d ago), licensed MIT. It adds 757 tokens to every session, about $0.0038 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.

Hardware and IoT ai-agent ardupilot drone mavlink mavsdk mcp

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

mavlink-mcp: Instructions file for Claude Code