What are the runtime dependencies for my-mcp-ssh?
Python >= 3.12 and the uv package manager are required.
@ffpy
基本信息
MCP-based SSH tool for LLMs to interact with remote servers.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"my-mcp-ssh": {
"command": "uv",
"args": [
"sync"
]
}
}
}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。
my-mcp-ssh is a Model Context Protocol (MCP) based SSH connection tool that allows large language models to securely connect to remote servers via SSH and perform file operations through the MCP protocol.
Clone the repository, install dependencies with uv sync, then configure the MCP client with the command uv --directory <your_path>/my-mcp-ssh run src/main.py. SSH connection parameters are set via environment variables (e.g., SSH_HOST, SSH_PASSWORD). Use the provided tools (connect, disconnect, list_sessions, execute, upload, download) to manage sessions and transfer files.
Python >= 3.12 and the uv package manager are required.
Set environment variables such as `SSH_HOST`, `SSH_PORT`, `SSH_USERNAME`, and either `SSH_PASSWORD` (for password auth) or `SSH_KEY_PATH` (for key auth).
It provides tools to connect, disconnect, list sessions, execute commands, upload files, and download files.
Run `./inspector.sh` from the project directory for online debugging.
It is licensed under the Apache License, Version 2.0.
Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

JiCo for Jira & Confluence: local MCP server for Jira Data Center - redacts personal data before the AI model, holds every write for approval

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
评论