πŸ’»

Code Sandbox

πŸ”΄Dangerous
Development

Execute code securely in isolated sandbox environments using the E2B API.

STEP 1

Understand what it does

Tell your agent things like:

β†’β€œuse code sandbox”
β†’β€œwrite code”
β†’β€œreview code”
β†’β€œmanage repository”
PERMISSIONS

What this capability can access

This capability requires the following permissions:

This capability has elevated permissions including Execute Code. Review the permissions below carefully before granting access to your agent.

⚑
Execute Code
Runs arbitrary code or scripts
πŸ“–
Read Files
Reads local files and directories
✏️
Write/Delete Files
Creates, modifies, or deletes files
🌐
Read External Data
Fetches data from external sources
πŸ“€
Send Data Externally
Sends data to external services
STEP 2

Set it up

Available on 1 platform. Pick yours:

MCP (Model Context Protocol)Docs

Add to your MCP client configuration:

{
  "mcpServers": {
    "code-sandbox": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-code-sandbox"]
    }
  }
}
STEP 3

Go deeper

Full documentation and source code

Add to your README

Show that your tool is listed on AgentSift

Code Sandbox trust score on AgentSift
[![AgentSift](https://agentsift.com/api/badge/capability/code-sandbox)](https://agentsift.com/capabilities/code-sandbox)

Options: ?style=flat-square for square corners, ?score=false for simple β€œlisted” badge

#mcp#development#agent-tool

Related capabilities