Skip to content
mcp/skillhub

Sandbox as a Service MCP Server

by fstandhartingercom.sandbox-as-a-service/mcpv1.1.0

Dedicated Linux VM sandboxes for untrusted, model-generated code: run commands, move files, expose a preview URL and destroy the VM.

0Node.jsstdioofficial registry

context tax

queued

security

queued

cold start

queued

freshness

Maintained32d ago

Install Sandbox as a Service MCP server

No published package or hosted endpoint yet — see the repository README for build-from-source instructions.

Configuration

VariableRequiredSecretDescription
AAS_API_KEYyesyesAPI key from https://sandbox-as-a-service.com/dashboard/keys

Freshness

Maintained — last maintenance signal 32d ago. The newest of the signals below sets the band.

  1. Last commit (default branch)

    2026-09-08 · 32d ago · GitHub

  2. Latest release

    2026-08-22 · 48d ago · GitHub · mcp-v1.1.0

  3. Package published

    no data · npm/PyPI

  4. Registry entry updated

    2026-08-22 · 48d ago · official registry · v1.1.0

FAQ

›Does Sandbox as a Service require an API key?

Yes. It expects AAS_API_KEY, of which 1 is a secret.

›Can I use Sandbox as a Service as a remote (hosted) MCP server?

No hosted endpoint is published; it runs locally over stdio.

›Is Sandbox as a Service in the official MCP registry?

Yes, as com.sandbox-as-a-service/mcp.

Alternatives to Sandbox as a Service

Other code execution & sandboxes MCP servers.

View all
REAActiveReverse engineer anything from your terminal or agent with one CLI and MCP server.Ask JevActiveA private persistent computer: files and a bash shell that survive between runs.Container UseMaintainedContainerized environments for coding agents: each agent works in its own fresh container and git branch, with execution history and terminal access.MATLABActiveConnect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.LLM SandboxActiveSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.QgisAbandonedconnects QGIS Desktop to Claude AI through the MCP. This integration enables prompt-assisted project creation, layer loading, code execution, and more.