E2B MCP

E2B sandboxed code execution — let AI run Python, JavaScript, and other code safely in isolated cloud environments.

TRUSTED · Security verified

// Add to your client

{
  "mcpServers": {
    "e2b": {
      "command": "npx",
      "args": ["-y", "@e2b/mcp-server"],
      "env": {
        "E2B_API_KEY": "<your-e2b-api-key>"
      }
    }
  }
}

{
  "mcpServers": {
    "e2b": {
      "command": "npx",
      "args": ["-y", "@e2b/mcp-server"],
      "env": {
        "E2B_API_KEY": "<your-e2b-api-key>"
      }
    }
  }
}

claude mcp add e2b -e E2B_API_KEY=<your-key> -- npx -y @e2b/mcp-server

Paste into your client's MCP configuration file.

// Try it now

"Run a quick Python script in the E2B sandbox that prints the first 10 Fibonacci numbers"

! E2B is usage-based — sandboxes are billed by runtime
! Each sandbox is ephemeral — state doesn't persist between runs unless you save it
! Installing large dependencies each run is slow — consider prebuilt templates

Setup

Easy Setup

API key or simple config

Token usage

Light usage

// When to use

You want your AI to actually execute code to verify output, not just write it
You're doing data analysis and want AI to run pandas/numpy on a sample
You're building agents that need a safe scratch environment
You want code to run without polluting your local machine

// When NOT to use

You want to run code in your local environment — do that directly
You need to process gigabytes of data — sandboxes have resource limits
You want long-running services (sandboxes are ephemeral)

// Usage Scenarios

Verified Code Execution

Have AI run the code it wrote and show you the actual output.

Example prompt

"Write a Python script to deduplicate this CSV, run it in the sandbox, and show me the result"

Data Analysis

Run pandas or numpy analysis on sample data in a clean environment.

Example prompt

"Take this sales CSV, run some exploratory analysis in pandas, and summarize the findings"

Sandboxed Testing

Test commands or scripts without risking your local setup.

Example prompt

"Try installing a weird NPM package in the sandbox and see if it does anything suspicious"

// About

Plain English

Imagine your AI being able to say 'let me actually run this Python code' and execute it in a safe cloud sandbox — then show you the result. This server connects your AI to E2B, a secure cloud environment where it can run code, test scripts, and use real tools without touching your machine.

The E2B MCP server enables AI assistants to execute code in secure, sandboxed cloud environments. Run Python, JavaScript, R, and other languages without local setup. Supports file operations, package installation, and persistent state within sessions.

Ideal for data analysis, scientific computing, and scenarios where you want AI to run and verify code before returning results.

GitHub 2.8kUpdated Feb 9, 2025Apache-2.0

View on GitHub Official Site

// Use Cases

Execute Python data analysis scripts with AI
Run and test code snippets in isolated environments
Perform scientific computations through conversation
Build and validate AI-generated code safely

// Works With

Claude Cursor Cline

#e2b#code-execution#sandbox#python#jupyter

// Also Consider

Docker MCP Trusted

When you can run sandboxed code locally in containers instead of paying for hosted sandboxes

→

// Related Servers

Anthropic Claude API MCP

Use Claude API within Claude — chain AI calls, compare model outputs, and build sophisticated multi-agent workflows.

View →

Git MCP

Official Git MCP server — read repository history, diffs, blame, and status through AI without leaving your conversation.

devtools

View →

Featured

Memory MCP

Official persistent memory server for AI — store facts, preferences, and context across conversations using a knowledge graph.

View →