What authentication method does MCP SSH Docker Server use?
It uses SSH key‑based authentication; place your private key in `./config/id_rsa` and add the public key to the remote host’s `authorized_keys`.
@aweher
Basic information
MCP server to play with IA and containerlab instances
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-ssh-frr": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
MCP SSH Docker Server is a Message Control Protocol (MCP) server that enables SSH and Docker command execution on remote systems and containers. It provides a standardized interface for operators and developers to run commands, stream output, and handle long-running tasks.
Install via pip install mcp-ssh-frr or from source, then configure SSH environment variables (SSH_HOST, SSH_USER, SSH_PORT) and place your private key in ./config/id_rsa. Start the server with python mcp_ssh_docker_server.py and use the ssh_exec and ssh_exec_docker tools with the required arguments.
It uses SSH key‑based authentication; place your private key in `./config/id_rsa` and add the public key to the remote host’s `authorized_keys`.
SSH connection timeout is 10 seconds, command execution timeout is 30 seconds, and stream maximum time is 300 seconds (5 minutes).
Yes, set the `structured_output` argument to `true` in either `ssh_exec` or `ssh_exec_docker` to receive a JSON response with exit code, stdout, stderr, duration, and metadata.
Call `ssh_exec_docker` with the argument `"list_containers": true`; it will return a list of containers on the remote host.
Python 3.7+, SSH access to the target system, and Docker installed on the target system if you intend to use Docker commands.

Windframe MCP gives your AI the design taste needed to create consistent, production-ready UI that feels intentionally designed. Available at https://windframe.dev/mcp

MCP-first toolbox for agents: namespaced key-value storage, a FIFO queue, auth, and a handful of stateless utility tools (JWT decode, hashing, cert inspection, CIDR math). Free while in early access. This repository is a
Unipile MCP server: LinkedIn MCP (Sales Navigator, Recruiter), WhatsApp, Instagram, Telegram and email MCP for coding agents. Build your LinkedIn, WhatsApp and email API integration from Cursor, Claude Code, Codex.
Open-source MCP server for Google Play developer workflows. Runs locally with your own credentials.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments