What programming languages are supported?
Python (subprocess), JavaScript (eval), and SQL (in-memory SQLite).
@Br0ski777
基本情報
Execute Python, JavaScript, or SQL in a sandbox. Get stdout, execution time, errors. 10s timeout. -- x402 micropayment API + MCP server for AI agents
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"code-sandbox": {
"url": "https://code-sandbox-production-9b5e.up.railway.app/mcp",
"transport": "sse"
}
}
}POST
Code Sandbox X402 executes Python, JavaScript, or SQL code in a sandboxed environment and returns stdout, execution time, errors, and exit codes. It uses a pay-per-call model via the x402 protocol (USDC on Base L2), requiring no API key, signup, or rate-limit wall. It is part of the klymax402 marketplace of micropayment APIs for AI agents.
Add the server to an MCP client configuration (Claude Desktop, Cursor, ElizaOS) using the URL https://code-sandbox.api.klymax402.com/mcp. Alternatively, call the HTTP endpoint directly with a POST request; any x402-aware client automatically handles the 402 payment challenge and retry cycle.
Python (subprocess), JavaScript (eval), and SQL (in-memory SQLite).
The default timeout is 5,000 ms, with a maximum of 10,000 ms.
Payment uses the x402 protocol – a HTTP-native pay-per-call system – on Base L2 (network `eip155:8453`) with USDC. No signup or API key is required; the first request returns a 402 challenge, and an x402‑aware client automatically signs and retries.
Yes, stdout is capped at 10 KB.
It is part of the klymax402 marketplace. The full API reference and catalog are available at klymax402.com.
This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent
Agentic SWMM is an automated, auditable, and memory-informed framework for reproducible stormwater modelling, integrating QGIS and EPA SWMM through the aiswmm runtime, reusable Skills, and MCP interfaces, with QA verification, provenance tracking, calibration support, and Codex,
A suite of Model Context Protocol (MCP) servers designed to enhance AI agent capabilities. Provides tools for media search/understanding (images, video), web information retrieval, PDF generation, and PowerPoint presentation creation, enabling agents to interact with diverse data
Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.
An MCP server that allows you to run TypeScript, JavaScript, and Python code in a sandbox on your local machine using the Deno® sandbox. This server provides a controlled environment for executing code with explicit permission controls.
コメント