mcpsshclient

2 starsMITCommunity

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

An MCP server SSHClient with a configurable agentic security agent that can detect and prevent unsafe commands from executing through your SSH connection.

README.md

![MseeP.ai Security Assessment Badge](https://mseep.ai/app/jonnadul-mcpsshclient)

mcpsshclient

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: