Kiro CLI Sandbox
Cosmonic Desktop is a local AI sandbox for Kiro CLI: the code Kiro writes is compiled to WebAssembly and runs on your own machine with no access to your files, network, or keys until you grant it. Two settings wire it up, one for launching Kiro from Builder with the sandbox playbook and one for installing Desktop's MCP server into Kiro; use either or both.
Sandbox Kiro CLI with Cosmonic Desktop
1. Settings → Agents: launch Kiro from Builder
Open Settings → Agents. The Detected agents card lists every coding agent Desktop found by its home directory (~/.kiro) or on your login shell's PATH, and says whether each one is launchable from Builder. In the Skills card, turn on Kiro CLI to install the cosmonic-sandbox skill at ~/.kiro/skills/cosmonic-sandbox/. This is the same install the one-time Set up your coding agents dialog offers on first run; nothing is installed silently.
The skill is the sandbox playbook: it teaches Kiro to compile what it generates to a WebAssembly component and deploy it into the local sandbox instead of running it raw on your host. Once it is installed, Builder can launch Kiro directly: open Builder, pick Kiro as the agent, describe what you want, and its output lands in a sandboxed workload you can inspect before it runs.
Kiro reads the open Agent Skills standard from ~/.kiro/skills, so the skill Desktop installs there is picked up natively the next time Kiro starts.
2. Settings → MCP Server: install Desktop's MCP server into Kiro
Open Settings → MCP Server. Under Install in your AI client, turn on Kiro CLI: Desktop's toggle writes the standard mcpServers entry into ~/.kiro/settings/mcp.json, the user-level file Kiro reads (the legacy ~/.aws/amazonq/mcp.json is migrated there when Kiro installs). This registers cosmonicd mcp serve as an MCP server in Kiro's own configuration, and the cosmonic_* tools (observe, deploy, build) are available the next time you start it. Expand Instructions on the same card to copy the manual snippet instead.
To do it by hand, add the server to ~/.kiro/settings/mcp.json:
{
"mcpServers": {
"cosmonic": {
"command": "/Applications/Cosmonic Desktop.app/Contents/Resources/cosmonicd",
"args": ["mcp", "serve"]
}
}
}3. Verify the connection
kiro-cli chat # then ask Kiro to list Cosmonic workloads; the cosmonic_* tools should answerStart kiro-cli chat and ask it to list Cosmonic workloads; the cosmonic_* tools answer while Desktop is running. Builder launches Kiro with --trust-tools=read by default (a guarded mode), with "Ask every time" and "Trust all tools" as alternatives.
Skills over MCP
Desktop's MCP server also publishes its skill family—cosmonic-sandbox, cosmonic-go, cosmonic-nats, cosmonic-nats-tuning, and cosmonic-kafka—through the MCP Skills extension (io.modelcontextprotocol/skills). A client that supports Skills over MCP gets the playbooks the moment it connects, with nothing written to its skills directory, so the MCP registration above is enough on its own for those clients. The on-disk skill from Settings → Agents covers clients that read a skills directory but do not yet speak the extension, and it is what Builder relies on to launch Kiro.
What Kiro can do once connected
Its full tool surface (observe, deploy, build) and the guardrails are covered in Connect Coding Agents; the tools work only while Cosmonic Desktop is running.
Frequently asked questions
How do I sandbox Kiro CLI?
Install Cosmonic Desktop, then under Settings → Agents turn on Kiro CLI to install the cosmonic-sandbox skill, and under Settings → MCP Server register Desktop’s MCP server in Kiro. From then on the code Kiro writes is compiled to WebAssembly and runs in a local sandbox with no access to your files, network, or keys until you grant it.
Does Kiro itself run inside the sandbox?
No. Kiro keeps running in your terminal or IDE exactly as before. What changes is where its output executes: the programs and MCP servers it builds run as sandboxed WebAssembly workloads on your machine instead of directly on your host.
Do I need both the skill and the MCP server?
They do different jobs. The MCP server gives Kiro the tools to build, deploy, and observe sandboxed workloads; the skill gives it the know-how to use them by default. Desktop also publishes its skills over the MCP Skills extension, so a client that supports Skills over MCP gets the playbook from the connection alone.
What can the code Kiro writes reach inside the sandbox?
Nothing by default. Each workload starts with no filesystem, network, or credential access; you grant exactly the capabilities it needs in its manifest, and everything else stays denied. The same manifest deploys unchanged to Cosmonic Control on Kubernetes.
Which Kiro trust mode does Builder use?
Builder starts Kiro CLI with --trust-tools=read by default: reads are trusted, everything else asks. You can switch to "Ask every time" or "Trust all tools" when you launch; the sandbox boundary around the code Kiro produces is the same in every mode.
Next steps
- The server's trust model and tool reference: Connect Coding Agents.
- Sandbox the tool servers your agent calls: Sandbox MCP Servers.
- What an AI sandbox is and why it matters: AI Sandbox.