MCP Sandbox: Your JavaScript Module in a Secure Environment 🛡️

Created By
TrHung1910a year ago
MCP Sandbox transforms JavaScript modules into secure MCP servers, enabling AI systems to access functions safely. With automatic reflection and type inference, it simplifies the integration process for developers. 🛠️💻
Overview

What is MCP Sandbox?

MCP Sandbox is a tool that transforms JavaScript modules into secure MCP (Model Context Protocol) servers, allowing AI systems to access functions safely while ensuring a secure environment for applications.

How to use MCP Sandbox?

To use MCP Sandbox, clone the repository, install dependencies, and run the application. You can create a JavaScript module and set up a sandboxed server to interact with it in real-time.

Key features of MCP Sandbox?

  • Sandboxed Environment: Run JavaScript modules securely.
  • Automatic Reflection: Access properties and methods easily.
  • Type Inference: Automatically get type information.
  • MCP Support: Seamless implementation of the Model Context Protocol.
  • CLI Tool: Command-line interface for module interaction.
  • Security Sandbox: Protect against harmful code execution.
  • Server-Sent Events: Efficient handling of real-time updates.
  • VM Isolation: Separate execution environments for enhanced security.

Use cases of MCP Sandbox?

  1. Running untrusted JavaScript code safely.
  2. Integrating AI functionalities into applications.
  3. Automating tasks with JavaScript modules.

FAQ from MCP Sandbox?

  • Can MCP Sandbox run any JavaScript module?

Yes, it can run any JavaScript module in a secure environment.

  • Is MCP Sandbox free to use?

Yes, MCP Sandbox is open-source and free to use.

  • How does MCP Sandbox ensure security?

It uses a sandboxed environment and VM isolation to protect against malicious code.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
TrHung1910
Star
0
Language
TypeScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

4 hours ago
Gpt Scrambler

a day ago