About mcpsshclient
mcpsshclient is an MCP server for SSH connections, with an optional agentic security agent that detects and blocks unsafe commands. The security agent can be configured with a policy and uses Ollama with llama2.
Key features
- 01SSH client over MCP
- 02Optional command security agent
- 03Configurable security policy
Use cases
- 01Connect to hosts through SSH from an MCP client
- 02Detect and prevent unsafe SSH commands
MCP support
It exposes SSH client capabilities to MCP clients. The README documents configuration for Claude Desktop, Cursor AI, and VSCode Insider.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcpsshclient
An MCP server SSHClient with a configurable :fireworks:agentic:fireworks: security agent that can detect and prevent "unsafe" commands from executing through your SSH connection.
Prerequisite
To enable the agentic capabilities.
- Download https://ollama.com/.
- Run
ollama serve - Run
ollama pull llama2 - Run
ollama run llama2
Setup Instructions
- Run
git clone https://github.com/jonnadul/mcpsshclient.git - Run
npm install - Run
npm run build
To enable the security agent, set "ENABLE_SECAGENT": true and "SECURITY_POLICY" in secagentconfig.json
Configuration
In your MCP Client make the corresponding change
{
"mcpServers": {
"sshclient": {
"command": "node",
"args": [
"C:\\[full-path-to-mcpsshclient]\\build\\index.js"
]
}
}
}
So far tested on the following:
- Claude Desktop:
claude_desktop_config.json - Cursor AI: Command Panel -> Cursor Settings -> MCP Server
- VSCode Insider
Have (responsible) fun! :rocket:
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
