Terminal MCP Server
Execute commands on local or remote hosts via SSH. Supports session persistence and environment variables.
Terminal MCP Server
Notice 注意事项
Current Project not in maintance anymore. I recommend you guys to use more advanced command tool —— Desktop Commander
当前项目已经不在维护。我建议大家用更先进的终端MCP工具 Desktop Commander
Terminal MCP Server is a Model Context Protocol (MCP) server that allows executing commands on local or remote hosts. It provides a simple yet powerful interface for AI models and other applications to execute system commands, either on the local machine or on remote hosts via SSH.
Features
- Local Command Execution: Execute commands directly on the local machine
- Remote Command Execution: Execute commands on remote hosts via SSH
- Session Persistence: Support for persistent sessions that reuse the same terminal environment for a specified time (default 20 minutes)
- Environment Variables: Set custom environment variables for commands
- Multiple Connection Methods: Connect via stdio or SSE (Server-Sent Events)
Installation
Installing via Smithery
To install terminal-mcp-server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @weidwonder/terminal-mcp-server --client claude
Manual Installation
# Clone the repository
git clone https://github.com/weidwonder/terminal-mcp-server.git
cd terminal-mcp-server
# Install dependencies
npm install
# Build the project
npm run build
Usage
Starting the Server
# Start the server using stdio (default mode)
npm start
# Or run the built file directly
node build/index.js
Starting the Server in SSE Mode
The SSE (Server-Sent Events) mode allows you to connect to the server remotely via HTTP.
# Start the server in SSE mode
npm run start:sse
# Or run the built file directly with SSE flag
node build/index.js --sse
You can customize the SSE server with the following command-line options:
| Option | Description | Default |
|---|---|---|
--port or -p | The port to listen on | 8080 |
--endpoint or -e | The endpoint path | /sse |
--host or -h | The host to bind to | localhost |
Example with custom options:
# Start SSE server on port 3000, endpoint /mcp, and bind to all interfaces
node build/index.js --sse --port 3000 --endpoint /mcp --host 0.0.0.0
This will start the server and listen for SSE connections at http://0.0.0.0:3000/mcp.
Testing with MCP Inspector
# Start the MCP Inspector tool
npm run inspector
The execute_command Tool
The execute_command tool is the core functionality provided by Terminal MCP Server, used to execute commands on local or remote hosts.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| command | string | Yes | The command to execute |
| host | string | No | The remote host to connect to. If not provided, the command will be executed locally |
| username | string | Required when host is specified | The username for SSH connection |
| session | string | No | Session name, defaults to "default". The same session name will reuse the same terminal environment for 20 minutes |
| env | object | No | Environment variables, defaults to an empty object |
Examples
Executing a Command Locally
{
"command": "ls -la",
"session": "my-local-session",
"env": {
"NODE_ENV": "development"
}
}
Executing a Command on a Remote Host
{
"host": "example.com",
"username": "user",
"command": "ls -la",
"session": "my-remote-session",
"env": {
"NODE_ENV": "production"
}
}
Configuring with AI Assistants
Configuring with Roo Code
- Open VSCode and install the Roo Code extension
- Open the Roo Code settings file:
~/Library/Application Support/Code/User/globalStorage/rooveterinaryinc.roo-cline/settings/cline_mcp_settings.json - Add the following configuration:
For stdio mode (local connection)
{
"mcpServers": {
"terminal-mcp": {
"command": "node",
"args": ["/path/to/terminal-mcp-server/build/index.js"],
"env": {}
}
}
}
For SSE mode (remote connection)
{
"mcpServers": {
"terminal-mcp-sse": {
"url": "http://localhost:8080/sse",
"headers": {}
}
}
}
Replace localhost:8080/sse with your actual server address, port, and endpoint if you've customized them.
Configuring with Cline
- Open the Cline settings file:
~/.cline/config.json - Add the following configuration:
For stdio mode (local connection)
{
"mcpServers": {
"terminal-mcp": {
"command": "node",
"args": ["/path/to/terminal-mcp-server/build/index.js"],
"env": {}
}
}
}
For SSE mode (remote connection)
{
"mcpServers": {
"terminal-mcp-sse": {
"url": "http://localhost:8080/sse",
"headers": {}
}
}
}
Configuring with Claude Desktop
- Open the Claude Desktop settings file:
~/Library/Application Support/Claude/claude_desktop_config.json - Add the following configuration:
For stdio mode (local connection)
{
"mcpServers": {
"terminal-mcp": {
"command": "node",
"args": ["/path/to/terminal-mcp-server/build/index.js"],
"env": {}
}
}
}
For SSE mode (remote connection)
{
"mcpServers": {
"terminal-mcp-sse": {
"url": "http://localhost:8080/sse",
"headers": {}
}
}
}
Best Practices
Command Execution
- Before running commands, it's best to determine the system type (Mac, Linux, etc.)
- Use full paths to avoid path-related issues
- For command sequences that need to maintain environment, use
&&to connect multiple commands - For long-running commands, consider using
nohuporscreen/tmux
SSH Connection
- Ensure SSH key-based authentication is set up
- If connection fails, check if the key file exists (default path:
~/.ssh/id_rsa) - Make sure the SSH service is running on the remote host
Session Management
- Use the session parameter to maintain environment between related commands
- For operations requiring specific environments, use the same session name
- Note that sessions will automatically close after 20 minutes of inactivity
Error Handling
- Command execution results include both stdout and stderr
- Check stderr to determine if the command executed successfully
- For complex operations, add verification steps to ensure success
Important Notes
- For remote command execution, SSH key-based authentication must be set up in advance
- For local command execution, commands will run in the context of the user who started the server
- Session timeout is 20 minutes, after which the connection will be automatically closed
Related Servers
Scout Monitoring MCP
sponsorPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP Devkit
A persistent development partner that prevents context drift and maintains project memory across all development sessions.
MCP Playground
A demonstration MCP server implementation in Go featuring real-time bidirectional file communication.
Credential Manager
A server for securely managing API credentials locally through the Model Context Protocol (MCP).
JSON MCP
MCP server empowers LLMs to interact with JSON files efficiently. With JSON MCP, you can split, merge, etc.
JFrog MCP Server
Interact with the JFrog Platform API for repository management, build tracking, and release lifecycle management.
zeuxis
Let AI agents capture screenshots themselves
Currents
Enable AI Agents to fix Playwright test failures reported to Currents.
Kaggle MCP
Get access to Kaggle's datasets, models, competitions, notebook and benchmarks.
esp-mcp
An MCP server for ESP-IDF workflows, enabling project builds, firmware flashing, and automated issue resolution from build logs.
IDA Pro
Interact with IDA Pro for reverse engineering and binary analysis tasks.