ssh-mcp-server: Secure Remote SSH for AI Workflows

What does “ssh-mcp-server” MCP Server do?

ssh-mcp-server is a bridging tool that enables AI assistants and other applications supporting the Model Context Protocol (MCP) to execute remote SSH commands through a standardized interface. By acting as a secure intermediary, it allows AI assistants to safely operate remote servers, execute commands, and retrieve results without directly exposing SSH credentials to AI models. The server supports multiple secure SSH connection methods, including password and private key authentication (with optional passphrase support). It also provides command security controls through blacklist and whitelist mechanisms, and enables bidirectional file transfer between local and remote servers. ssh-mcp-server is designed for seamless integration into development workflows, providing developers and AI agents with powerful, controlled access to remote systems for tasks such as maintenance, automation, and deployment.

List of Prompts

No prompt templates are explicitly mentioned in the available documentation.

List of Resources

No explicit resources are documented in the available files or README.

List of Tools

• execute-command
  Command Execution Tool: Execute SSH commands on remote servers and get results.
• upload
  File Upload Tool: Upload local files to specified locations on remote servers.
• download
  File Download Tool: Download files from remote servers to local specified locations.

Use Cases of this MCP Server

• Remote Server Management
  Enables developers or AI agents to securely execute administrative or maintenance commands on remote servers, such as restarting services, checking logs, or updating software.
• Automated Deployment
  Facilitates automated deployment pipelines by allowing scripts or AI workflows to push code, run setup scripts, or manage applications over SSH.
• File Synchronization
  Supports bidirectional file transfer, making it easy to upload configuration files or download logs and results from remote servers.
• Security Auditing
  Permits controlled execution of audit commands (using whitelist/blacklist), enabling safe security checks and compliance validation without risk of damaging the system.
• Credential Isolation
  Allows safe operation by ensuring SSH credentials are never exposed to the AI model, reducing risk in sensitive environments.

How to set it up

Windsurf

1. Prerequisites: Ensure you have Node.js and npx installed.
2. Locate Configuration: Open your Windsurf configuration file.
3. Add MCP Server: Insert the following JSON snippet into your mcpServers object:

   {
     "mcpServers": {
       "ssh-mpc-server": {
         "command": "npx",
         "args": [
           "-y",
           "@fangjunjie/ssh-mcp-server",
           "--host 192.168.1.1",
           "--port 22",
           "--username root",
           "--password pwd123456"
         ]
       }
     }
   }
   

4. Save and Restart: Save the file and restart Windsurf.
5. Verify Setup: Test by running a simple SSH command via the MCP interface.

Claude

1. Prerequisites: Node.js and npx should be available.
2. Locate Configuration: Open Claude’s mcpServers configuration.
3. Add MCP Server: Use the following configuration:

   {
     "mcpServers": {
       "ssh-mpc-server": {
         "command": "npx",
         "args": [
           "-y",
           "@fangjunjie/ssh-mcp-server",
           "--host 192.168.1.1",
           "--port 22",
           "--username root",
           "--privateKey ~/.ssh/id_rsa"
         ]
       }
     }
   }
   

4. Save and Restart: Save your changes and restart Claude.
5. Verify Setup: Attempt a test command through Claude’s MCP integration.

Cursor

1. Prerequisites: Install Node.js and npx.
2. Edit Configuration: Go to the Cursor configuration directory and edit the appropriate file.
3. Add MCP Server: Insert:

   {
     "mcpServers": {
       "ssh-mpc-server": {
         "command": "npx",
         "args": [
           "-y",
           "@fangjunjie/ssh-mcp-server",
           "--host 192.168.1.1",
           "--port 22",
           "--username root",
           "--privateKey ~/.ssh/id_rsa",
           "--passphrase pwd123456"
         ]
       }
     }
   }
   

4. Restart Cursor: Save and restart Cursor.
5. Verify: Use the MCP command palette to verify remote SSH connectivity.

Cline

1. Prerequisites: Make sure Node.js and npx are installed.
2. Open Config: Edit the mcpServers section in Cline’s configuration.
3. Add MCP Server: Add:

   {
     "mcpServers": {
       "ssh-mpc-server": {
         "command": "npx",
         "args": [
           "-y",
           "@fangjunjie/ssh-mcp-server",
           "--host 192.168.1.1",
           "--port 22",
           "--username root",
           "--password pwd123456",
           "--whitelist ^ls( .*)?,^cat .*,^df.*"
         ]
       }
     }
   }
   

4. Save and Restart: Save the config and restart Cline.
5. Test Connection: Validate by running an allowed command.

Securing API Keys

To avoid exposing credentials in configuration files, use environment variables:

{
  "mcpServers": {
    "ssh-mpc-server": {
      "command": "npx",
      "args": [
        "-y",
        "@fangjunjie/ssh-mcp-server",
        "--host ${SSH_HOST}",
        "--port ${SSH_PORT}",
        "--username ${SSH_USER}",
        "--password ${SSH_PASSWORD}"
      ],
      "env": {
        "SSH_HOST": "192.168.1.1",
        "SSH_PORT": "22",
        "SSH_USER": "root",
        "SSH_PASSWORD": "pwd123456"
      }
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "ssh-mpc-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “ssh-mpc-server” to your actual MCP server name and update the URL.

Overview

Our opinion

ssh-mcp-server provides essential SSH functionality as an MCP server, focused on security and convenience. Its toolset is practical for many development and automation scenarios, but lacks advanced features like resources, prompt templates, or sampling support. The documentation is clear for setup and operational use. Overall, it’s a solid, specialized utility for secure SSH access via MCP.

MCP Score

RATING: 5/10

The ssh-mcp-server scores moderately, excelling in secure SSH integration and core tool exposure, but lacks resource and prompt support, and does not document roots or sampling features. Its open-source license and clear setup are positives, but it remains a focused, rather than comprehensive, MCP solution.