e2b-sandbox-mcp: Instructions file for Claude Code

CLAUDE.md

e2b-sandbox-mcp CLAUDE.md is an instructions file for Claude Code from asif-nvc/e2b-sandbox-mcp. It costs 830 tokens per session, scanned A, original, MIT.

Setup instructions for an MCP server that gives Claude Code access to isolated cloud Linux machines called E2B sandboxes. These machines can clone repositories, run commands, manage files, and perform Git operations.

In plain words
What is it for?
Use it to build, register, and configure the server, including its API keys and optional access for private repositories and Git pushes.
Why use it?
It lets coding work run in a separate environment instead of changing the local computer.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is asif-nvc/e2b-sandbox-mcp's own configuration. It tells Claude Code how to work on e2b-sandbox-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything e2b-sandbox-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to asif-nvc/e2b-sandbox-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/asif-nvc/e2b-sandbox-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/asif-nvc/e2b-sandbox-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for e2b-sandbox-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/asif-nvc/e2b-sandbox-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/asif-nvc/e2b-sandbox-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/asif-nvc/e2b-sandbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/asif-nvc/e2b-sandbox-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for e2b-sandbox-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/asif-nvc/e2b-sandbox-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/asif-nvc/e2b-sandbox-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 830 This file is loaded in full into every session.
When invoked 830 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00830 $0.00830
Opus 5 $0.00415 $0.00415
Sonnet 5 $0.00166 $0.00166
Haiku 4.5 $0.00083 $0.00083

Measured 10d ago against content hash 09ee9b69dbd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

e2b-sandbox-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What This Is

An MCP (Model Context Protocol) server that gives Claude Code access to E2B cloud sandboxes — isolated Linux VMs for cloning repos, running commands, managing files, and performing git operations without touching the local machine. Communicates over stdio transport.

Build & Run

npm run build          # TypeScript → dist/
npm run dev            # Build + run
npm start              # Run from dist/ (must build first)

No test suite or linter is configured.

Register as MCP Server

claude mcp add e2b-sandbox -s user \
  -e E2B_API_KEY=your-key \
  -e GITHUB_TOKEN=your-token \
  -- node /absolute/path/to/dist/index.js

Environment Variables

  • E2B_API_KEY (required) — from e2b.dev/dashboard. Without it, sandbox_create fails immediately.
  • GITHUB_TOKEN (optional) — enables private repo cloning and git push. Auto-configured on sandbox creation via sandbox.git.dangerouslyAuthenticate().

Architecture

Single-process MCP server, ESM ("type": "module"), strict TypeScript targeting ES2022/Node16.

Entry point: src/index.ts — creates McpServer, registers all tool groups, connects via StdioServerTransport.

Singleton sandbox registry: src/services/sandbox-manager.tsSandboxManager class holds a Map<sandboxId, {sandbox, info}> of live E2B Sandbox instances. All tools look up sandboxes by ID through this registry. Stale sandbox detection happens in commands.ts (catches "not found" errors, removes from registry).

Tool registration pattern: Each file in src/tools/ exports a register*Tools(server: McpServer) function that calls server.tool() with Zod schemas for input validation. Four tool groups (29 tools total):

  • sandbox.ts — lifecycle (create, list, info, kill, keep_alive, pause, resume) + networking (get_url, upload_url, download_url)
  • commands.ts — exec, exec_background (with output truncation at 100KB per stream), process_list, process_kill
  • filesystem.ts — read, write, list (capped at 1000 entries), mkdir, remove, info, exists, rename
  • git.ts — clone (shallow depth=1 by default), status, commit, push, pull, branch, init

Read the full file on GitHub · 64 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 64 lines · 830 tokens per session scan A 09ee9b69dbd7

Subscribe to this mod's changes

e2b-sandbox-mcp CLAUDE.md is an instructions file published in the GitHub repository asif-nvc/e2b-sandbox-mcp (3 stars, last pushed 4mo ago), licensed MIT. It adds 830 tokens to every session, about $0.0042 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens