Command Palette

Search for a command to run...

UnylyUnyly
Browse all

Ashlar

FreeNot checked

Build AI-powered Minecraft Paper servers with MCP tools—no SSH, no mods, just one jar and a URL.

GitHubEmbed

About

Build AI-powered Minecraft Paper servers with MCP tools—no SSH, no mods, just one jar and a URL.

README

🧱 ashlar - Your Minecraft Server's AI Builder

⬇️ Download Ashlar

AI assistants (Claude, ChatGPT, Cursor) survey, render, build, and inspect your live Minecraft Paper server through MCP.


✨ What Is Ashlar?

Ashlar is a bridge between your Minecraft server and AI assistants. It lets AI tools like Claude, ChatGPT, and Cursor connect directly to your Paper server. The AI can look at your world, place blocks, build structures, and check what is happening in real time.

Think of it as giving a smart robot access to your Minecraft world. You describe what you want ("build a castle entrance"), and the AI uses Ashlar to do it for you. No coding, no command blocks, just plain language.


🏗️ What Can You Do With It?

🧭 Survey Your World

  • AI can see the terrain around you
  • Check biomes, structures, and buildable areas
  • Understand what blocks are where

🎨 Render and Visualize

  • Get 3D views of your build area
  • See what the AI is planning before it places anything
  • Share images of your world with the AI for better results

🛠️ Build on Command

  • Tell the AI "make a 10x10 house with oak walls"
  • The AI builds it block by block on your live server
  • Perfect for fanciers, redstone contraptions, or landscaping

🔍 Inspect and Debug

  • Check block data, entities, and server states
  • See what is wrong with a build or mechanism
  • Get real-time feedback about your server environment

🚀 Getting Started (Windows)

📥 Step 1: Download Ashlar

Visit this link to download the application:

🔗 Get Ashlar Now

When you click the link, you will land on the Ashlar GitHub page. Look for the "Releases" section (usually on the right side of the page) and download the latest version file.

Your download should complete in a few seconds or minutes depending on your internet speed.

📂 Step 2: Locate the Downloaded File

Open your Downloads folder. You should see a file named something like ashlar.zip (or similar). This is a compressed package containing everything you need.

🗜️ Step 3: Extract the File

  1. Right-click on the .zip file.
  2. Choose "Extract All..." from the menu.
  3. A window will appear asking where to extract. Click "Extract" at the bottom.
  4. A new folder will appear with the Ashlar files inside.

🖥️ Step 4: Run Ashlar

  1. Open the extracted folder.
  2. Look for an executable file (it will have an icon and no extension, or ends in .exe).
  3. Double-click it to start Ashlar.

If Windows shows a blue popup saying "Windows protected your PC," click "More info" then "Run anyway". This is normal for new applications that are not yet widely known.


🔧 What You Need Before Starting

Ashlar needs three things to work:

1. 🎮 A Minecraft Paper Server

  • You need a Paper server (version 1.20.4 or newer recommended)
  • If you do not have one, search "how to set up a Paper Minecraft server on Windows" — plenty of easy guides exist
  • Your server should be running while you use Ashlar

2. 🧠 An AI Assistant

  • Claude Desktop (claude.ai) or ChatGPT with MCP support
  • Cursor (for code-based work)
  • Make sure you have one of these installed and logged in

3. 🔌 A Connection Between Them

  • Ashlar acts as the middle-man
  • It provides a link (MCP endpoint) that your AI assistant connects to
  • Follow the on-screen instructions in Ashlar for the exact address

📝 How to Use Ashlar (Simple Example)

Step 1: Start your Minecraft Paper server.

Step 2: Open Ashlar on your computer. It will show you a connection URL (something like http://localhost:3456).

Step 3: In your AI assistant, open the MCP settings or add a new server connection.

Step 4: Paste the URL from Ashlar into the MCP connection field.

Step 5: Save and connect. You should see a green "Connected" indicator.

Step 6: In the AI chat, type something like:

"Look at the area near my player. Build a small stone bridge across the river, 3 blocks wide."

The AI will survey, plan, and build it automatically on your live server.


💡 Tips for Best Results

Tip Why It Helps
Be specific in your requests "Build a 5x5 wooden house with a door" works better than "build a house"
Let the AI survey first Say "Survey the area" before asking for a build
Use block names correctly "Oak planks", "stone bricks", "glowstone"
Start small Test with tiny builds before complex projects
Keep server running Ashlar only works when the server is up

❓ Frequently Asked Questions

Q: Is Ashlar free?

Yes, Ashlar is free to download and use.

Q: Do I need to know programming?

No. Ashlar handles all the technical stuff. You just type what you want in plain English.

Q: Will it work with my existing Minecraft world?

Yes. Ashlar connects to your live Paper server and can build anywhere in your world.

Q: Is it safe?

Ashlar runs locally on your machine, only connecting to your own server and your chosen AI assistant. Always download from the official GitHub link provided above.

Q: I got a Windows SmartScreen warning. What do I do?

Click "More info" → "Run anyway". This happens with many new applications because they are not yet digitally signed with a trusted certificate.

Q: Can multiple AI assistants use Ashlar at once?

Yes, Ashlar supports multiple simultaneous connections.


🆘 Troubleshooting

Problem: AI says "Cannot connect"

  • Check the link is still running
  • Make sure your Paper server is online
  • Restart both Ashlar and your AI assistant

Problem: Builds are in wrong location

  • Ask the AI to "survey the area" first so it sees the correct coordinates
  • Be clear about where you want the build (e.g., "next to the blacksmith shop", "north of spawn")

Problem: No blocks appear

  • Confirm you are on a Paper server (not a vanilla server)
  • Check the server has enable-command-block=true in server.properties
  • Restart the server after making changes

📊 System Requirements

  • Operating System: Windows 10 or Windows 11 (64-bit)
  • RAM: 4 GB minimum (8 GB recommended for larger worlds)
  • Java: Java 17 or newer (required for Paper server)
  • Network: Internet connection for AI service
  • Storage: 500 MB free space

📜 License

Ashlar is released under the MIT License. You are free to use, modify, and distribute it. The underlying Minecraft server and AI services have their own licenses and terms.


💬 Community & Support

For help, bugs, or feature requests:

  • Open an issue on the GitHub repository
  • Join discussions in the repository's Discussions tab
  • Check the repository for updated documentation

🤝 Contributing

If you are a developer and want to add features or fix bugs, fork the repository and submit a pull request. Check the repository structure for development instructions.


📁 Project Status

Ashlar is actively developed. Check the repository for release notes, changelogs, and upcoming features. Star the repository to show support and stay updated.


Keywords: ai, ai-agents, bukkit, claude, java, llm, mcp, mcp-server, minecraft, minecraft-building, minecraft-plugin, minecraft-server, model-context-protocol, paper, papermc, typescript

from github.com/oscarobua47/ashlar

Installing Ashlar

This server has no published package — it is built from source. Open the repository and follow its README.

▸ github.com/oscarobua47/ashlar

FAQ

Is Ashlar MCP free?

Yes, Ashlar MCP is free — one-click install via Unyly at no cost.

Does Ashlar need an API key?

No, Ashlar runs without API keys or environment variables.

Is Ashlar hosted or self-hosted?

Self-hosted: the server runs locally on your machine via the install command above.

How do I install Ashlar in Claude Desktop, Claude Code or Cursor?

Open Ashlar on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.

Related MCPs

Compare Ashlar with

Not sure what to pick?

Find your stack in 60 seconds

Author?

Embed badge for your README

Browse similar

All ai MCPs