メニュー
Add sandboxed code execution to any MCP-compatible AI client. E2B gives agents access to secure, internet-connected Linux environments for running Python, JavaScript, and shell commands without touching your local machine.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | E2B Code Execution MCP |
| slug | e2b-code-execution-mcp |
| description | Add sandboxed code execution to any MCP-compatible AI client. E2B gives agents access to secure, internet-connected Linux environments for running Python, JavaScript, and shell commands without touching your local machine. |
| github_stars | 393 |
| verification | security_reviewed |
| source | https://github.com/e2b-dev/mcp-server |
| author | E2B |
| publisher_type | individual |
| category | Developer Tools |
| framework | MCP |
| tool_ecosystem | {"github_repo":"e2b-dev/mcp-server","github_stars":393,"npm_package":"@e2b/mcp-server","npm_weekly_downloads":5344} |
Add sandboxed code execution to any MCP-compatible AI client. E2B gives agents access to secure, internet-connected Linux environments for running Python, JavaScript, and shell commands without touching your local machine.
MCP-compatible client (Claude Code, Cursor, or similar), E2B API key, Node.js runtime
Use the upstream install or setup path that matches your environment:
Requirements and caveats from upstream:
Extracted from upstream docs: https://raw.githubusercontent.com/e2b-dev/mcp-server/HEAD/README.md
Use Vocode to compose transcription, LLM, speech synthesis, and telephony components into reviewable real-time voice-agent workflows.
Use Claude Legal Skill to guide an agent through contract risk review, CUAD-style clause checks, market benchmarks, and lawyer-ready redline suggestions.
Use SWE-ReX when a coding agent needs a consistent runtime interface for local, containerized, or remote shell sessions with command output, exit codes, interactive tools, and parallel execution.
Use Text Extract API when an agent needs to turn PDFs, Office files, or images into Markdown or structured JSON with local OCR, optional Ollama models, PII removal, and queued batch processing.
Route model calls through Helicone, inspect costs, latency, traces, prompts, and evaluations, then review changes before they ship.
Launch an OpenAI-compatible OpenLLM server for a chosen open model, point an agent runtime at it, and compare behavior before production use.
