@mq1n
Injectable MCP server for AI-driven reverse engineering inside processes
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"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"
]
}
}
}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。
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.
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.
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.
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.
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.
Destructive commands require a safety token. Call `safety_request_token` first, then include the returned `token_id` in the destructive operation’s arguments.
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.
Open-source MCP to use Blender with any LLM
B2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
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.
不止于 CSS
评论