Mcpsshclient
What is Mcpsshclient
mcpsshclient is an SSH client that complies with the Model Context Protocol (MCP), featuring a configurable security agent designed to detect and prevent unsafe commands from executing through SSH connections.
Use cases
Use cases for mcpsshclient include secure remote access to servers, development environments requiring strict command execution policies, and integration with AI tools that leverage SSH for operations.
How to use
To use mcpsshclient, first download and run Ollama by executing ‘ollama serve’, then pull and run the Llama2 model. Clone the mcpsshclient repository, install dependencies with ‘npm install’, and build the project using ‘npm run build’. Finally, configure the security agent in ‘secagentconfig.json’ and set the appropriate parameters in your MCP Client configuration.
Key features
Key features of mcpsshclient include a security agent that enhances command safety, compliance with MCP standards, and compatibility with various platforms like Claude Desktop, Cursor AI, and VSCode Insider.
Where to use
mcpsshclient can be used in environments where secure SSH connections are critical, such as software development, cloud computing, and remote server management.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Mcpsshclient
mcpsshclient is an SSH client that complies with the Model Context Protocol (MCP), featuring a configurable security agent designed to detect and prevent unsafe commands from executing through SSH connections.
Use cases
Use cases for mcpsshclient include secure remote access to servers, development environments requiring strict command execution policies, and integration with AI tools that leverage SSH for operations.
How to use
To use mcpsshclient, first download and run Ollama by executing ‘ollama serve’, then pull and run the Llama2 model. Clone the mcpsshclient repository, install dependencies with ‘npm install’, and build the project using ‘npm run build’. Finally, configure the security agent in ‘secagentconfig.json’ and set the appropriate parameters in your MCP Client configuration.
Key features
Key features of mcpsshclient include a security agent that enhances command safety, compliance with MCP standards, and compatibility with various platforms like Claude Desktop, Cursor AI, and VSCode Insider.
Where to use
mcpsshclient can be used in environments where secure SSH connections are critical, such as software development, cloud computing, and remote server management.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
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.
- 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:
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
