mcpField
C
Code Sandbox X402

Code Sandbox X402

Remote
github.comAI & Agents0Updated 8w ago

About Code Sandbox X402

Code Sandbox X402 is an MCP server for AI agents to run Python, JavaScript, or SQL in a sandbox and receive output, timing, and error details. Calls use x402 pay-per-call payments.

Key features

  1. 01Sandboxed Python, JavaScript, and SQL execution
  2. 02Returns stdout and execution time
  3. 03Provides exit code and error details
  4. 04Execution timeout up to 10 seconds
  5. 05x402 pay-per-call payments

Use cases

  1. 01Run calculations and retrieve results
  2. 02Transform data and inspect output
  3. 03Validate code snippets
  4. 04Query an in-memory SQLite database

MCP support

The server exposes the `code_execute_sandbox` tool to MCP clients for submitting code and a language and retrieving execution results. The README provides a remote MCP URL and client configuration example.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://code-sandbox.api.klymax402.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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 README

Code Sandbox API

MCP Server x402 License: MIT

Execute Python, JavaScript, or SQL in a sandbox. Get stdout, execution time, errors. 10s timeout. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

{
  "mcpServers": {
    "code-sandbox": {
      "url": "https://code-sandbox.api.klymax402.com/mcp"
    }
  }
}

Quickstart -- HTTP (x402)

curl -X POST "https://code-sandbox.api.klymax402.com/api/execute" \
  -H "Content-Type: application/json" \
  -d '{"code":"...","language":"..."}'
# -> 402 Payment Required, with an x402 payment challenge in the response body

Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.

Tools

ToolMethodPathPriceDescription
code_execute_sandboxPOST/api/execute$0.02Execute code in a sandboxed environment
code_execute_sandbox

Use this when you need to execute Python, JavaScript, or SQL code in a sandboxed environment and get the output. Supports Python (subprocess), JavaScript (eval), and SQL (in-memory SQLite).

Parameters

NameTypeRequiredDescription
codestringyesThe code to execute
languagestringyesProgramming language: python, javascript, or sql
timeoutnumbernoExecution timeout in milliseconds (default: 5000, max: 10000)

Returns

  • output -- stdout captured from code execution (max 10KB)
  • language -- the language that was executed
  • executionTimeMs -- execution duration in milliseconds
  • exitCode -- process exit code (0 = success)
  • error -- error message if execution failed (null on success)

Example response:

{"output":"Hello World\n42\n","language":"python","executionTimeMs":234,"exitCode":0,"error":null}

When to use: running calculations, data transformations, validating code snippets, or querying in-memory databases. Essential when you need computed results rather than static data.

Example agent prompts

  • "Execute Python, JavaScript, or SQL code in a sandboxed environment and get the output"

Payment

  • Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
  • Network: Base L2 (eip155:8453)
  • Asset: USDC
  • Facilitator: Coinbase CDP (primary), PayAI (fallback)
  • Also reachable via ATXP (OAuth-wrapped x402, RFC 9728 protected-resource metadata)

Part of klymax402

100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.

License

MIT

Comments

Markdown supported

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.