Build and run your agent's code, sandboxed.
Your coding agent writes code faster than you can read it. Cosmonic Desktop is a local AI sandbox: it runs MCP servers and agent code on your own machine, where each one starts with no access to your files, network, or keys until you grant it.
No account required· Run your first sandbox in minutes
Build with your agent
Prompt to a sandboxed app, instantly
Bring your own coding agent. Install the cosmonic-sandbox skill, or connect Desktop's MCP server, and the code your agent writes lands in a sandbox you can read before it runs. Your app is compiled locally and runs in a sandbox from the first second.
Tiny footprint
Fast enough to sandbox everything,
small enough to run it all
A fresh sandbox per call is cheap, and idle workloads cost nothing. Secure every tool your agent touches without compromises.
Under the hood, each workload is a WebAssembly component running on CNCF wasmCloud, so you can deploy at scale and you're never locked in.
How it works
Code only gets what you grant
Every workload starts with zero authority: no filesystem, no network, no environment, no clock. It gets exactly the capabilities you grant and nothing else, so a poisoned tool or an injected instruction has nowhere to go. Open Inspect to see the whole boundary before anything runs.
Can reachonly what you granted
Never grantednever requested, never reachable
In the box
Everything you need to run agent code locally
Three ways to start
Get started in minutes
Install Desktop and pick a starting point. Whichever you choose, the code runs deny-by-default and you see its boundary before it starts.
Pull from the Launchpad
Grab a ready-made, already-sandboxed app or MCP server from the built-in catalog and deploy it in a click. Review what it can reach, then run it.
Describe an app to the Builder
Say what you want in plain language. Your coding agent builds and deploys in a sandbox.
Give your agent a sandboxed tool
Build an MCP server and register it with Claude Code, Cursor, and other agents in one step. Your agent gets a new tool in your sandbox.
FAQ
Running agent code safely,
answered
Is it safe to run the code my AI coding agent writes?
The risk isn't the agent; it's the code and MCP servers it runs. Cosmonic Desktop runs each of them in its own WebAssembly sandbox with deny-all egress: no access to your files, network, or keys until you grant it.
How do I set up a Claude Code sandbox?
Install Cosmonic Desktop and connect it to Claude Code with its MCP server. Claude Code then builds and runs its code and MCP servers as sandboxed workloads on your machine, each starting with deny-all egress. The Claude Code sandbox guide walks through the setup.
How do I sandbox an MCP server for Claude Code or Cursor?
Run the MCP server as a Cosmonic Desktop workload. It starts with no file, network, or credential access; you grant exactly the capabilities it needs, and everything else stays denied.
How do I run an MCP server locally?
Cosmonic Desktop runs MCP servers on your own machine (no cloud sandbox required), each isolated with deny-all egress by default. It's free on macOS, Windows, and Linux.
Is Cosmonic Desktop free, and which platforms does it run on?
Yes. Cosmonic Desktop is free and runs on macOS, Windows, and Linux. It's currently in public beta.
Cleared for launch
Download Cosmonic Desktop and run your first sandboxed workload in minutes. Free forever for personal use, local, and yours.
macOS · Windows · Linux
It's an early beta. Expect a few rough edges, and tell us what breaks.