tree_main
by treeAgentic MCP SSHClient: Secure SSH Command Execution
Overview
The Agentic MCP SSHClient is a specialized MCP server SSH client designed to enhance security by detecting and preventing the execution of "unsafe" commands through your SSH connection. It integrates a configurable agentic security agent to ensure responsible and secure command execution.
Prerequisites
To enable the agentic capabilities, follow these steps:
1. Download and install Ollama.
2. Run ollama serve.
3. Run ollama pull llama2.
4. Run ollama run llama2.
Setup Instructions
- Clone the repository:
bash git clone https://github.com/jonnadul/mcpsshclient.git - Build the project:
bash npm run build
Configuration
To enable the security agent, modify the secagentconfig.json file:
- Set "ENABLE_SECAGENT": true.
- Define the "SECURITY_POLICY" according to your requirements.
In your MCP client, update the configuration as follows:
{
"mcpServers": {
"sshclient": {
"command": "node",
"args": [
"C:\\[full-path-to-mcpsshclient]\\build\\index.js"
]
}
}
}
Compatibility
The Agentic MCP SSHClient has been tested with the following tools:
- Claude Desktop: Modify claude_desktop_config.json.
- Cursor AI: Access the Command Panel -> Cursor Settings -> MCP Server.
About
The Agentic MCP SSHClient is an open-source project licensed under the MIT License. It is designed to provide a secure and agentic approach to SSH command execution.
Topics
Resources
Project Activity
- Stars: 1
- Watchers: 1
- Forks: 0
No releases or packages have been published yet.
Languages
- TypeScript: 100.0%
Invite Gmail Contacts
