About SandboxAPI
SandboxAPI MCP Server lets MCP-compatible AI clients run code in eight languages inside isolated gVisor-sandboxed Docker containers. It provides single and batch execution with network access disabled and resource limits enforced.
Key features
- 01Execute code in eight languages
- 02Run multiple snippets in isolated sandboxes
- 03Set timeout and standard input
- 04List language versions and examples
- 05Network-isolated, ephemeral execution
Use cases
- 01Run generated code without local execution
- 02Test snippets in different languages
- 03Compare multiple code snippets in batch
- 04Use standard input to test program behavior
MCP support
Exposes execute_code, execute_batch, and list_languages tools to MCP clients. It can be accessed through a hosted remote endpoint or run via Docker or from source.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.sandboxapi.dev/mcpclaude mcp add --transport http michielderuiter-sandboxapi https://mcp.sandboxapi.dev/mcp{"mcpServers":{"michielderuiter-sandboxapi":{"type":"http","url":"https://mcp.sandboxapi.dev/mcp"}}}Open in Cursor{"servers":{"michielderuiter-sandboxapi":{"type":"http","url":"https://mcp.sandboxapi.dev/mcp"}}}Open in VS Code{"mcpServers":{"michielderuiter-sandboxapi":{"type":"http","url":"https://mcp.sandboxapi.dev/mcp"}}}{"mcpServers":{"michielderuiter-sandboxapi":{"serverUrl":"https://mcp.sandboxapi.dev/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMESandboxAPI MCP Server
Give your AI agent the ability to execute code in 8 programming languages, safely.
SandboxAPI MCP Server connects any MCP-compatible AI client (Claude, Cursor, VS Code, Windsurf, etc.) to secure code execution. Every execution runs inside a gVisor-sandboxed Docker container with no network access, strict resource limits, and ephemeral filesystems.
Quick Start
Option 1: Remote Server (No Setup)
Connect directly to the hosted endpoint. No local installation required.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"sandboxapi": {
"url": "https://mcp.sandboxapi.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
VS Code (.vscode/mcp.json):
{
"servers": {
"sandboxapi": {
"url": "https://mcp.sandboxapi.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Cursor (~/.cursor/mcp.json):
{
"mcpServers": {
"sandboxapi": {
"url": "https://mcp.sandboxapi.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Option 2: Docker
docker run -d \
-p 8081:8081 \
-e SANDBOXAPI_API_KEY=your_sandboxapi_key \
-e MCP_API_KEY=your_mcp_auth_key \
sandboxapi/mcp:latest
Then point your client to http://localhost:8081/mcp.
Option 3: Build from Source
git clone https://github.com/sandboxapi/sandboxapi-mcp.git
cd sandboxapi-mcp
go build -o sandboxapi-mcp .
export SANDBOXAPI_API_KEY=your_key
export MCP_API_KEY=optional_auth_key
./sandboxapi-mcp
Available Tools
execute_code
Execute code in a sandboxed container.
| Parameter | Type | Required | Description |
|---|---|---|---|
language | string | Yes | python3, javascript, typescript, bash, java, cpp, c, go |
code | string | Yes | Source code to execute (max 1MB) |
timeout | number | No | Timeout in seconds (default: 10, max: 300) |
stdin | string | No | Standard input to pass to the program |
execute_batch
Execute multiple code snippets. Each runs in its own isolated sandbox.
| Parameter | Type | Required | Description |
|---|---|---|---|
executions | array | Yes | Array of {language, code, timeout?, stdin?} objects |
list_languages
List all supported programming languages with versions and example code. No parameters.
Supported Languages
| Language | Version | Aliases |
|---|---|---|
| Python | 3.12 | python3, python, py |
| JavaScript | Node 22 | javascript, js, node |
| TypeScript | 5.4 | typescript, ts |
| Go | 1.22 | go, golang |
| Java | 21 | java, jdk |
| C++ | GCC 14 | cpp, c++ |
| C | GCC 14 | c, gcc |
| Bash | 5.2 | bash, sh, shell |
Environment Variables
| Variable | Required | Description |
|---|---|---|
SANDBOXAPI_API_KEY | Yes | API key for the SandboxAPI backend |
MCP_API_KEY | No | Auth key for the MCP endpoint (omit for open access) |
MCP_PORT | No | Port to listen on (default: 8081) |
SANDBOXAPI_URL | No | API base URL (default: https://api.sandboxapi.dev) |
Security
Every code execution is isolated with defense-in-depth:
- gVisor (runsc) — User-space kernel intercepts all syscalls
- Network isolation — Executed code cannot make outbound connections
- Resource limits — CPU, memory, and disk usage are capped
- Ephemeral containers — Destroyed immediately after execution
- Read-only filesystem — No persistent writes between executions
- Code size limits — Source code capped at 1MB
- Timeout enforcement — Hard kill after configured timeout
API Key
Get your API key at sandboxapi.dev or through RapidAPI.
Links
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.