English Français العربية

ScratchRun

Official registry Developer tools

Ephemeral MicroVM-isolated code execution for AI agents. Fresh VM per call, hard-purged after.

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

NPM package @scratchrun/mcp-server
Claude Code 
claude mcp add scratchrun -e 'SCRATCHRUN_API_KEY=<your scratchrun_api_key>' -- npx -y @scratchrun/mcp-server@0.1.1
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "scratchrun": {
            "command": "npx",
            "args": [
                "-y",
                "@scratchrun/mcp-server@0.1.1"
            ],
            "env": {
                "SCRATCHRUN_API_KEY": "<your scratchrun_api_key>"
            }
        }
    }
}

Environment variables

  • SCRATCHRUN_API_KEY required secret ScratchRun API key — get one at https://scratchrun.dev

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. @scratchrun/mcp-server
  2. Install
  3. Tool: scratchrun_exec
  4. Isolation
  5. Latency
  6. License

@scratchrun/mcp-server

MCP server for ScratchRun — ephemeral, MicroVM-isolated code execution for AI agents.

Each call runs in a fresh hardware-isolated MicroVM. The VM is hard-purged after execution. No state, no files, nothing persists between calls.

Install

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "scratchrun": {
      "command": "npx",
      "args": ["-y", "@scratchrun/mcp-server"],
      "env": {
        "SCRATCHRUN_API_KEY": "sr_live_your_key_here"
      }
    }
  }
}

Get an API key at scratchrun.dev.

Tool: scratchrun_exec

Executes code in an ephemeral sandbox and returns stdout, stderr, exit code, and any output files.

Parameters:

ParameterTypeRequiredDescription
runtimepython3.12 \python3.11 \node20 \bashyesRuntime to use
codestringyesCode to execute
timeout_msintegernoTimeout in ms (default 10000, max 30000)
memory_mbintegernoMemory limit in MB (default 256, max 512)
envobjectnoEnvironment variables — use for secrets, not code strings
filesobjectnoFiles to write before execution (path → content)
return_filesstring[]noFile paths to capture after execution (returned as base64)

Example — run Python and return a chart:

{
  "runtime": "python3.12",
  "code": "import matplotlib.pyplot as plt\nimport numpy as np\nx = np.linspace(0, 10, 100)\nplt.plot(x, np.sin(x))\nplt.savefig('/tmp/plot.png')",
  "return_files": ["/tmp/plot.png"]
}

Output files are returned as base64. Image files (PNG, JPG, SVG) are returned as MCP image content blocks and render inline in Claude.

Isolation

  • Hardware-virtualized MicroVM per execution (own kernel, not a shared-kernel container)
  • TerminateMicroVM called unconditionally after every run — VM destroyed, never reused
  • RFC 1918 + cloud metadata (169.254.x.x) always blocked at the network layer
  • Read-only system filesystem via OverlayFS; /tmp is RAM-backed and gone with the VM

Latency

~400ms median (warm pool). 2–8s cold start if the pool is empty.

License

MIT

Frequently asked questions

What is ScratchRun?

Ephemeral MicroVM-isolated code execution for AI agents. Fresh VM per call, hard-purged after.

How do I install ScratchRun?

It runs on your machine. In Claude Code: claude mcp add scratchrun -e 'SCRATCHRUN_API_KEY=<your scratchrun_api_key>' -- npx -y @scratchrun/mcp-server@0.1.1. For other clients, paste the JSON configuration from this page into their MCP settings.

Does ScratchRun need an API key?

Yes. It expects SCRATCHRUN_API_KEY, which you set in its configuration.

Is ScratchRun open source?

Its code is public on GitHub, but the repository does not declare a standard license.

Who maintains ScratchRun?

It is published by ar-blues. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.