What are the runtime dependencies?
Python 3.8+, PostgreSQL 12+, Redis (for the task queue), and an SSH API Service for device communication.
@RobertBergman
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ssh-mcp-server-robertbergman": {
"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.
The SSH MCP Server is a centralized management system for network devices. It leverages an SSH API to execute commands on switches, providing advanced network monitoring, configuration validation, and reporting capabilities.
Clone the repository, set up a Python virtual environment, install dependencies, configure environment variables (e.g., DATABASE_URL, REDIS_HOST, SSH_API_URL), create the PostgreSQL database, run Alembic migrations, and start the server with uvicorn app.main:app. Once running, access the interactive API documentation at http://localhost:8000/api/v1/docs.
Python 3.8+, PostgreSQL 12+, Redis (for the task queue), and an SSH API Service for device communication.
Device inventories, command outputs, and historical data are stored in a PostgreSQL database.
JWT token-based authentication with role-based access control. Device credentials are encrypted at rest.
The server exposes a REST API over HTTPS. Swagger UI and ReDoc documentation are available at `/api/v1/docs` and `/api/v1/redoc`.
The README does not specify any limitations of the server or the underlying SSH API.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Read-only Total CMS docs and site content over MCP: exact Twig signatures, field types, schema options, the CLI, release notes and comparisons. No key required.

Collide is the multiplayer layer for AI coding agents, and it pays for itself. Expert orchestration across every agent on your repo saves teams tens to hundreds of dollars a day in token burn. Run Claude Code, Codex, Cu

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

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark
Comments