广告合作
MCP.so
登录

MGC Blackbox – Local Encrypted Execution Layer MCP Server

@zkeviny

代码仓库

基本信息

分类

其他

传输方式

stdio

作者

zkeviny

提交者

YUAN YUAN

关于 MGC Blackbox – Local Encrypted Execution Layer MCP Server

A local encrypted execution layer for AI agents. Provides sealed scripts, protected subprocess execution, and secure local storage.

#encrypted#local#execution#subprocess#secure#storage#sandbox#blackbox

MGC Blackbox – Local Encrypted Execution Layer MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mgc-blackbox": {
      "command": "mgc",
      "args": [
        "--mcp"
      ]
    }
  }
}

MGC Blackbox – Local Encrypted Execution Layer MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MGC Blackbox – Local Encrypted Execution Layer?

MGC Blackbox – Local Encrypted Execution Layer is a local encrypted execution engine that protects sensitive human intent and enables secure, deterministic AI execution. It provides sealed script execution, protected subprocess execution, encrypted local storage, a capability sandbox, and three interaction interfaces (WebUI, API, MCP).

How to use MGC Blackbox – Local Encrypted Execution Layer?

Install via pip with the command pip install mgc-blackbox. For detailed installation and usage instructions, refer to the full documentation at the provided GitHub repository.

Key features of MGC Blackbox – Local Encrypted Execution Layer

  • Sealed script execution (encrypted, decrypted at runtime)
  • Protected subprocess execution in a controlled sandbox
  • Encrypted local storage with device-level encryption
  • Capability sandbox hides underlying logic from AI
  • Three interaction interfaces: WebUI, API, MCP
  • Serves as a trusted execution boundary for agents

Use cases of MGC Blackbox – Local Encrypted Execution Layer

  • Execute sensitive AI scripts without exposing plaintext logic.
  • Run local commands in a secure, sandboxed environment.
  • Store and process encrypted data for AI-driven tasks.
  • Provide a trusted boundary for agent orchestration.

常见问题

1

What is MGC Blackbox – Local Encrypted Execution Layer?

It is a local encrypted execution engine that protects sensitive human intent and enables secure, deterministic AI execution. It is not an agent but a trusted execution boundary for agents.

2

What features does MGC Blackbox provide?

It provides sealed script execution, protected subprocess execution, encrypted local storage, a capability sandbox, and three interaction interfaces (WebUI, API, MCP).

3

How do I install MGC Blackbox – Local Encrypted Execution Layer?

Install via pip with the command `pip install mgc-blackbox`.

4

Where can I find full documentation?

Full documentation is available at https://github.com/zkeviny/MGC-Blackbox.

5

How does MGC Blackbox relate to AI agents?

MGC Blackbox is not an agent; it serves as a trusted execution boundary for agents, allowing them to use capabilities without seeing the underlying logic.

评论

其他 分类下的更多 MCP 服务器

DeepMark

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Glasswarp

Glasswarp

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

🚀 Model Context Protocol (MCP) Curriculum for Beginners

microsoft

This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

16.7K
广告合作