Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

wassette

MCP.Pizza Chef: microsoft

Wassette works like a safety-checked app store for your AI assistant's toolbox. Once you connect it to GitHub Copilot, Claude Code, Codex CLI, or a similar assistant, you can ask it to load a small, single-purpose tool — such as one that tells the time or reads a file — and that tool runs inside a locked-down sandbox that can't reach beyond what it's allowed to touch. No account or API key is required to get started; you install the runtime once and then add new tools with a simple chat request.

Coding
Other

Use This MCP server To

Give my AI assistant a new skill without leaving the chat Load a ready-made tool from an online library in seconds Try new AI tools without risking my computer's files or data Ask my assistant to check the current time or date Keep experimental tools boxed in so they can't cause damage Add tools to Claude Code, GitHub Copilot, or Codex CLI

README

Wassette

A security-oriented runtime that runs WebAssembly Components via MCP

Quick Start | FAQ | Documentation | Releases | Contributing | Discord

Warning

Early Development: This repository is not production ready yet. It is in early development and may change significantly.

Why Wassette?

  • Convenience: Wassette makes it easy to extend AI agents with new tools, all without ever having to leave the chat window.
  • Reusability: Wasm Components are generic and reusable; there is nothing MCP-specific about them.
  • Security: Wassette is built on the Wasmtime security sandbox, providing browser-grade isolation of tools.

Architecture

An architecture diagram showing the relationship between Wassette, MCP Clients, and Wasm Components

Installation

Quick start: For Linux/macOS, use our one-liner install script:

curl -fsSL https://raw.githubusercontent.com/microsoft/wassette/main/scripts/install.sh | bash

For complete installation instructions for all platforms (including Windows, Homebrew, Nix, Docker, and more), see our Installation Guide.

Using Wassette

With Wassette installed, the next step is to register it with your agent of choice. See our Quick Start guide (3 simple steps), or check the MCP Clients guide for detailed setup instructions for GitHub Copilot, Copilot CLI, Claude Code, and Codex CLI.

Once configured, you can start loading WebAssembly components. To teach your agent to tell the time, ask it to load a time component:

Please load the time component from oci://ghcr.io/microsoft/time-server-js:latest

Now that the time component is loaded, we can ask your agent to tell you the current time:

What is the current time?

The agent will respond with the current time, which is fetched from the time component running in a secure WebAssembly sandbox:

The current time July 31, 2025 at 10:30 AM UTC

Congratulations! You've just run your first Wasm Component and taught your agent how to tell time!

Demo

wassette-in-60-seconds.mp4

Discord

You can join us via the #wassette channel on the Microsoft Open Source Discord:

Microsoft Open Source Discord

Contributing

Please see CONTRIBUTING.md for more information on how to contribute to this project.

License

This project is licensed under the MIT License.

Trademarks

This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.

Contributors

Thanks to all contributors who are helping shape Wassette into something great.

wassette FAQ

Can I use this to give my AI assistant new abilities without writing code?
Yes — you install Wassette once, then simply ask your assistant, in a normal chat message, to load a tool from an online library, and it becomes available right away.
Can I use this to try out a new AI tool safely before trusting it?
Yes — every tool runs inside a locked-down sandbox, so you can experiment with something new without worrying it will reach into the rest of your computer.
Which apps does this work with?
Wassette has been set up to work with GitHub Copilot, Copilot CLI, Claude Code, and Codex CLI, with more assistants expected to add support over time.
Do I need an account or a special key to use it?
No — no sign-up or API key was found to be required. You install the free runtime on your computer and start using it right away.
Is this safe for a non-technical person to use?
Yes — the tools it loads run in the same kind of protected sandbox that keeps a web browser tab from touching the rest of your computer, so a tool can't quietly change your files or settings.
How hard is it to set up?
You run a short one-line install command on Mac or Linux — Windows and other install options are also available — then point your AI assistant's settings at it; most people are up and running within a few minutes.
Where do the tools it loads come from?
They come from an online library of pre-built tools that developers have published; you ask your assistant to load one by name or address, and Wassette fetches and runs it for you.