MCP.so
ログイン
G

Ghostmcp MCP Server

@mq1n

基本情報

カテゴリ

その他

トランスポート

stdio

作者

mq1n

投稿者

Koray

Ghostmcp MCP Server について

Injectable MCP server for AI-driven reverse engineering inside processes

Ghostmcp MCP Server の設定

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": {
    "ghost-core": {
      "command": "path/to/ghost-core-mcp.exe",
      "args": [
        "--transport",
        "stdio"
      ]
    },
    "ghost-analysis": {
      "command": "path/to/ghost-analysis-mcp.exe",
      "args": [
        "--port",
        "13341"
      ]
    },
    "ghost-static": {
      "command": "path/to/ghost-static-mcp.exe",
      "args": [
        "--port",
        "13342"
      ]
    },
    "ghost-extended": {
      "command": "path/to/ghost-extended-mcp.exe",
      "args": [
        "--port",
        "13343"
      ]
    }
  }
}

Ghostmcp MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Ghostmcp?

Ghostmcp is an injectable MCP (Model Context Protocol) server for reverse engineering on Windows. It combines memory inspection, disassembly, debugging, and code injection into a single tool that any MCP-compatible AI client can use. Users inject it into a target process and interact through natural conversation.

How to use Ghostmcp?

Inject Ghostmcp into the target process and use an MCP-compatible AI client to issue natural-language commands. Launch one or all servers via the scripts/launch-mcp.ps1 script (agent listens on port 13338, core uses stdio, analysis/static on TCP). Destructive operations require a safety token: call safety_request_token and include the returned token_id.

Key features of Ghostmcp

  • Memory read/write with automatic type conversion
  • AOB and YARA pattern scanning
  • Full memory dump with PE reconstruction
  • Cheat Engine-style value and pointer scanning
  • Disassembly (Capstone) and decompilation (Hex-Rays style)
  • Software and hardware breakpoints, single stepping
  • Code injection and shellcode execution
  • Win32 API call tracing with argument decoding
  • AI‑friendly summaries, debugging sessions, and vulnerability hints

Use cases of Ghostmcp

  • Find and freeze a game's health value at a constant number
  • Locate all functions referencing a specific string in memory
  • Set a breakpoint on system calls and trigger notifications when hit
  • Disassemble a function at a given address and explain its logic
  • Discover all pointer paths leading to a particular address

よくある質問

1

What is Ghostmcp’s architecture?

Ghostmcp uses a modular multi‑server setup with four servers (ghost‑core‑mcp, ghost‑analysis‑mcp, ghost‑static‑mcp, ghost‑extended‑mcp) on ports 13340–13343, providing over 250 tools while staying under MCP client limits.

2

Is Ghostmcp stable for production use?

No – the project is labeled **EXPERIMENTAL**. APIs may change without notice, features may be incomplete or unstable, and documentation may not reflect the current state. Use at your own risk.

3

What runtime does Ghostmcp require?

It runs on Windows only. The README mentions scripts for PowerShell (`scripts/launch-mcp.ps1`) and requires an MCP‑compatible AI client to interact with the injected server.

4

How do I safely perform destructive operations?

Destructive commands require a safety token. Call `safety_request_token` first, then include the returned `token_id` in the destructive operation’s arguments.

5

What transports and authentication does Ghostmcp use?

The agent listens on TCP port 13338; the core server uses stdio, while analysis and static servers communicate over TCP. No authentication mechanism is described in the README.

コメント

「その他」の他のコンテンツ