mcpsshclient

mcpsshclient

By jonnadul GitHub

An Agentic MCP server sshclient

ssh security
Overview

What is mcpsshclient?

mcpsshclient is an MCP server SSH client that features a configurable agentic security agent designed to detect and prevent unsafe commands from executing through your SSH connection.

How to use mcpsshclient?

To use mcpsshclient, follow these steps:

  1. Download and run Ollama by executing ollama serve.
  2. Pull the Llama2 model with ollama pull llama2.
  3. Run the model using ollama run llama2.
  4. Clone the repository with git clone https://github.com/jonnadul/mcpsshclient.git and build it using npm run build.
  5. Configure the security agent in secagentconfig.json by setting "ENABLE_SECAGENT": true and defining the "SECURITY_POLICY".

Key features of mcpsshclient?

  • Configurable agentic security agent to enhance SSH security.
  • Ability to detect and prevent unsafe commands.
  • Integration with MCP servers for enhanced functionality.

Use cases of mcpsshclient?

  1. Secure SSH connections for remote server management.
  2. Preventing unauthorized command execution in sensitive environments.
  3. Enhancing security protocols in cloud-based applications.

FAQ from mcpsshclient?

  • Is mcpsshclient free to use?

Yes! mcpsshclient is open-source and free to use under the MIT license.

  • What programming language is mcpsshclient written in?

mcpsshclient is developed using TypeScript.

  • How can I contribute to mcpsshclient?

You can contribute by submitting issues or pull requests on the GitHub repository.

Content

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.

  1. Download https://ollama.com/.
  2. Run ollama serve
  3. Run ollama pull llama2
  4. Run ollama run llama2

Setup Instructions

  1. Run git clone https://github.com/jonnadul/mcpsshclient.git
  2. Run npm install
  3. 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:

No tools information available.

Banner grabbing with LLM (MCP Server)

python security
View Details

Asterisk Model Context Protocol (MCP) server.

python security
View Details

awsome kali MCPServers is a set of MCP servers tailored for Kali Linux, designed to empower AI Agents in reverse engineering and security testing. It offers flexible network analysis, target sniffing, traffic analysis, binary understanding, and automation, enhancing AI-driven workflows.

agent security
View Details
w3security-mcp
w3security-mcp by GoPlusSecurity

A web3 security mcp server for users

web3 security
View Details

A security scanner for your LLM agentic workflows

cli security
View Details

A network monitoring tool for MCP servers that logs all network activities to help identify potential security issues.

network-monitoring security
View Details

-

website-monitoring security
View Details