Sandboxd Code Run
Hosted one-shot code execution: send a snippet plus optional files, get stdout, stderr, exit...
使うべきか
品質と安全性
A
検出事項（2）
- LOWTool 'execute-code' doesn't follow camelCase/snake_caseexecute-code 内
- LOWTool 'execute-command' doesn't follow camelCase/snake_caseexecute-command 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
~597トークン数（ツール定義）
~2.8 KB一般的なレスポンスサイズ
注意への影響は最小限（128k コンテキストの 0.47%）
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"sandboxd-code-run": {
"url": "https://sandboxd-code-run.saastemly.com/mcp"
}
}
}リモートエンドポイント
https://sandboxd-code-run.saastemly.com/mcpstreamable-httpできること
ツール一覧
ツール（2）
🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
⚪execute-code(code, language, argv, env, timeout, ...)
Runs Python, JavaScript or TypeScript code in an isolated one-shot sandbox and returns stdout, stderr, exit code and artifacts (Daytona CodeRunRequest/ExecuteResponse compatible) Price: $0.002 a call.
入力スキーマ
{
"type": "object",
"properties": {
"code": {
"type": "string",
"description": "The code to run (up to 1 MB of UTF-8)"
},
"language": {
"type": "string",
"description": "\"python\", \"javascript\" or \"typescript\"",
"enum": [
"python",
"javascript",
"typescript"
]
},
"argv": {
"type": "array",
"items": {
"type": "string"
},
"description": "Command-line arguments for the program (sys.argv[1:] in Python, process.argv.slice(2) in Node)"
},
"env": {
"type": "object",
"description": "Environment variables; keys must match [A-Za-z_][A-Za-z0-9_]* (Daytona's rule)"
},
"timeout": {
"type": "integer",
"description": "Run timeout in seconds, 1-120 (default 60); a timed-out run answers exitCode 124"
},
"files": {
"type": "object",
"description": "Text files written into the work directory next to the program (up to 50, 1 MB each, 4 MB total); the entry point main.py/main.js/main.ts is reserved"
},
"outputs": {
"type": "array",
"items": {
"type": "string"
},
"description": "Relative paths to read back after the run (up to 20); up to 1 MB each comes back base64 in outputFiles, larger in tooLargeOutputs, absent in missingOutputs"
}
},
"required": [
"code",
"language"
]
}⚪execute-command(command, env, cwd, timeout, files, ...)
Runs a shell command in an isolated one-shot sandbox and returns stdout, stderr and the exit code (Daytona ExecuteRequest/ExecuteResponse compatible) Price: $0.002 a call.
入力スキーマ
{
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "The shell command to run (up to 64 KB)"
},
"env": {
"type": "object",
"description": "Environment variables; keys must match [A-Za-z_][A-Za-z0-9_]* (Daytona's rule)"
},
"cwd": {
"type": "string",
"description": "Working directory, relative to the run's work directory"
},
"timeout": {
"type": "integer",
"description": "Run timeout in seconds, 1-120 (default 60); a timed-out run answers exitCode 124"
},
"files": {
"type": "object",
"description": "Text files written into the work directory before the run (up to 50, 1 MB each, 4 MB total)"
},
"outputs": {
"type": "array",
"items": {
"type": "string"
},
"description": "Relative paths to read back after the run (up to 20); up to 1 MB each comes back base64 in outputFiles, larger in tooLargeOutputs, absent in missingOutputs"
}
},
"required": [
"command"
]
}コミュニティ
エビデンス
最近の観測
検証済みバージョンは記録されていませんツール 2 件