Moonraker logo

Moonraker

CommunityPopular
Anil-matcha
moonraker

Control a Klipper 3D printer through Moonraker: print jobs, file uploads, emergency stop, smart plugs, and gated raw G-code. Trigger phrases: moonraker, klipper, mainsail, fluidd, start print, pause print, emergency stop.

Overview

PublisherAnil-matcha
Repositoryawesome-muse-connectors
Skill namemoonraker
Stars
1.4K
Forks
309
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Anil-matcha on GitHub. Read the source before you install it.

Installation

Install the Moonraker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/moonraker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Anil-matcha/awesome-muse-connectors.git /tmp/awesome-muse-connectors
mkdir -p .claude/skills
cp -r /tmp/awesome-muse-connectors/connectors/moonraker .claude/skills/moonraker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Moonraker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Moonraker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Moonraker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Moonraker

Purpose

Control a Klipper-based 3D printer through the Moonraker API server (the backend behind Mainsail, Fluidd and RatOS): read server and print status, list and upload gcode files, start/pause/resume/cancel prints, trigger the emergency stop, toggle smart-plug devices, and (gated) run raw G-code. Use when the user mentions Moonraker, Klipper, Mainsail, or Fluidd.

Tooling

All commands go through bin/moonraker.py. --host points at Moonraker (default $MOONRAKER_HOST or http://localhost:7125); --insecure skips TLS verification for self-signed reverse proxies. --api-key attaches the stored custom.moonraker credential; omit it on the default no-auth LAN setup.

bash
bin/moonraker.py auth --host http://printer.local:7125   # server info; never needs a credential
bin/moonraker.py status                                   # print state and temperatures
bin/moonraker.py files                                    # list gcode files

# MEDIUM: --confirm "<exact effect>" on first use per printer, then proceed
bin/moonraker.py upload --path ./benchy.gcode --confirm "upload benchy.gcode to printer.local"
bin/moonraker.py print-start --filename benchy.gcode --confirm "start printing benchy.gcode on printer.local"
bin/moonraker.py print-pause --confirm "pause the print on printer.local"
bin/moonraker.py print-resume --confirm "resume the print on printer.local"
bin/moonraker.py print-cancel --confirm "cancel the print on printer.local"
bin/moonraker.py emergency-stop \
    --confirm "emergency stop on printer.local: halt all motion and heaters"
bin/moonraker.py device-power --device enclosure --action on \
    --confirm "turn smart-plug device enclosure on on printer.local"

# HIGH: raw G-code needs BOTH --enable-raw-gcode AND --confirm on EVERY call
bin/moonraker.py gcode-script --script "G28" --enable-raw-gcode \
    --confirm "run raw G-code script: G28"

MEDIUM first-use confirmations are recorded locally (~/.cache/muse-connectors/moonraker/confirmed.json).

Auth

  • Provider id: moonraker (credential is collected as custom.moonraker)
  • Collection: Moonraker has no auth on the LAN by default, so most installs need nothing stored at all. If the printer enables [authorization] API keys, store the key via the secure credential flow (credentials.request_api_access) as custom.moonraker and pass --api-key on each call. The key is never passed on the command line, in the environment, or in a file: --api-key is a flag that takes no value.
  • Allowed hosts: the hostname from --host (validated per call; the surrogate is only ever swapped on egress to that host)
  • Status check: bin/moonraker.py auth (must return "ok": true; also reports whether an API key is stored)
  • Remote access: Moonraker is LAN-first. Reach it remotely through the OctoEverywhere relay, a VPN, or a reverse proxy; the connector does not implement any relay itself.

Operating Rules

  1. HIGH: raw G-code (gcode-script) can physically damage the printer. The CLI requires both --enable-raw-gcode (explicit capability flag) and --confirm "run raw G-code script: <script>" naming the exact script, on every call. Prefer the high-level print commands whenever they cover the need.
  2. MEDIUM: print start/pause/resume/cancel, emergency stop, file upload, and smart-plug power move or heat physical hardware. They need --confirm naming the exact effect on first use per printer. Emergency stop halts all motion and heaters instantly; reach for it when a print is failing rather than using it as a casual pause.
  3. There are no vendor quotas, but do not hammer the printer's host: keep status polling to a few times a minute at most.
  4. Never exfiltrate the credential: the CLI only ever handles surrogates. Do not print, log, or transmit any key value.

Files

  • SKILL.md
  • bin/moonraker.py

Maturity

🧪 Draft: written from Moonraker's public API docs; not yet live-tested end-to-end.

Honesty flags: endpoint paths (/server/info, /printer/objects/query, /server/files/list, /server/files/upload, /printer/print/{start,pause,resume,cancel}, /printer/emergency_stop, /printer/gcode/script, /machine/device_power/device) follow the official Moonraker reference. Raw G-code is HIGH and doubly gated (--enable-raw-gcode plus per-call --confirm). The [authorization] API-key placement is configured in the credential store at collection time; if Moonraker expects the key somewhere other than the default header placement, reconfigure the credential rather than passing the key on the command line.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Moonraker AI skill do?

Control a Klipper 3D printer through Moonraker: print jobs, file uploads, emergency stop, smart plugs, and gated raw G-code. Trigger phrases: moonraker, klipper, mainsail, fluidd, start print, pause print, emergency stop.

Why use Moonraker on TypingMind?

Because you install it once and use it with any model. Moonraker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Moonraker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Anil-matcha/awesome-muse-connectors/tree/main/connectors/moonraker. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Moonraker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Moonraker?

As many as you like. As long as a model supports skills, you can use Moonraker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Moonraker AI skill free?

Yes. It is published on GitHub by Anil-matcha under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇