"A sandbox environment for running REPL code" matching MCP servers:

Enables AI agents to run untrusted, model-generated Python code in a locked-down throwaway Docker container with enforced isolation and resource limits. Supports starting, checking, and stopping asynchronous runs while returning structured status reports without exposing the host, network, or Docker controls.

Execute Python, JavaScript, or SQL code in a sandboxed environment and retrieve stdout, execution time, and errors with pay-per-call via x402 (USDC on Base L2).

A persistent Python REPL MCP server for AI agents with stateful execution, real timeouts, crash isolation, and an MCP bridge to call other tools in the project.

Enables coding agents and CI/CD pipelines to audit untrusted code by detecting Python sandbox escapes, SQL injection taint, ReDoS regex vulnerabilities, and CORS misconfigurations, while generating Seccomp BPF filters for safer execution.

Enables a sandboxed Claude Code session to see editor selections, review proposed edits as VS Code diffs, and read workspace diagnostics through an MCP-over-WebSocket IDE bridge.

Enables AI agents to run persistent Node.js REPL sessions that preserve state across evaluations, supporting top-level await, module loading, and per-session npm package installation.

一个基于MCP的Python REPL服务器，支持多会话管理、代码执行、历史记录回放和包安装，为AI提供Python解释器能力。

Enables running arbitrary JavaScript code in isolated Docker containers with on-demand npm dependency installation, allowing for ephemeral script execution and long-running services with controlled resource limits.

A secure JavaScript REPL server that enables executing code snippets in a sandboxed environment with memory protection, timeout handling, and comprehensive error reporting.

Bridges Claude Code CLI with Cursor IDE to use your existing Claude subscription without separate API costs.

This MCP server enables MCP clients such as Claude Desktop to run LLM-generated code in a secure, isolated sandbox across multiple container backends and programming languages.

Provides a persistent JavaScript kernel that treats any configured MCP server as a capability catalog, exposing all its tools to the model through just two tools (js and js_reset) while keeping the model-visible schema small and injecting host parameters like projectPath.

Enables agents to provision isolated Kubernetes runtimes where they can write files, run commands, start long-lived processes, and publish apps at authenticated URLs, all backed by per-user durable storage that outlives any runtime.

A local, keyless MCP server simulating Forge's industrial telemetry kernel, enabling agents to normalize vendor-specific machine data, forecast breaches, and test integrations against realistic equipment data without credentials or persistence.

Production-ready MCP server for secure Python code execution with artifact capture, virtual environment support, and LM Studio integration.

A public MCP server providing test fixtures for developers and QA, with a single tool 'identity' that returns a unique canary string to verify the server's response.

A sandbox MCP server for testing and debugging MCP tools and interactions via the MCP Inspector.

Enables Claude to create local, persistent mock REST APIs on demand from plain-language descriptions, with data written to disk so it survives restarts.

Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.

Connects AI assistants to the Sandbox Studio API to manage AWS sandbox accounts, leases, templates, events, and settings through natural language conversations.