iTerm MCP Server

What does “iTerm” MCP Server do?

The iTerm MCP Server is a Model Context Protocol (MCP) server implementation designed for integration with iTerm2, the popular terminal emulator for macOS. This server enables AI assistants to interact programmatically with iTerm2 terminals via MCP, allowing for seamless automation and terminal management within development workflows. By exposing terminal session management and command execution as MCP tools, the iTerm MCP Server empowers developers and AI agents to create, manage, and interact with terminal sessions, execute shell commands, read outputs, and handle multiple terminals dynamically. This integration enhances productivity by bridging LLM-driven automation and traditional terminal operations, making it valuable for use cases such as live code execution, log monitoring, and automated environment setup.

List of Prompts

No prompt templates are mentioned in the repository.

List of Resources

No explicit MCP resources are described in the repository.

List of Tools

• open_terminal: Open a new terminal instance in iTerm2.
• execute_command: Execute a shell command in a specific terminal session.
• read_output: Read and retrieve the output from a specific terminal.
• close_terminal: Close a specified terminal session.
• list_terminals: List all currently active terminals and their details.

Use Cases of this MCP Server

• Automated Development Environment Setup: Instantly open terminals and execute setup scripts or environment commands, reducing manual intervention for onboarding or repetitive tasks.
• Continuous Integration & Testing: Use AI to programmatically run tests, capture outputs, and manage build environments directly from the terminal.
• Live Log Monitoring: Open terminals that tail log files and allow an assistant to read outputs or alert developers of specific patterns or errors in real time.
• Remote Command Execution: Enable AI agents to run administrative or diagnostic commands, fetch outputs, and report back results for efficient system monitoring or troubleshooting.
• Terminal Session Management: Manage multiple terminal sessions (create, close, list) via AI, making it easier to orchestrate and coordinate complex multi-step workflows.

How to set it up

Windsurf

No setup instructions found for Windsurf.

Claude

No setup instructions found for Claude.

Cursor

1. Prerequisite: Ensure Node.js >= 14.x is installed and you are running macOS with iTerm2.

2. Open your ~/.cursor/mcp.json configuration file.

3. Add the iTerm MCP Server by inserting the following JSON snippet:

   {
     "mcpServers": {
       "terminal": {
         "command": "npx",
         "args": ["iterm_mcp_server"]
       }
     }
   }
   

4. Save the configuration file.

5. Restart Cursor to apply the changes.

6. Verify that the MCP server is running and connected to iTerm2.

Securing API Keys

No information about API key usage or configuration is provided in the repository.

Cline

No setup instructions found for Cline.

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:

{
  "iTerm": {
    "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 “iTerm” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The iTerm MCP Server provides a focused integration for iTerm2 terminal automation via MCP, with well-documented tools and easy configuration for Cursor. However, the lack of prompt templates, explicit resources, and details for platforms like Windsurf, Claude, or Cline, as well as omitted API key/security information, limits completeness. Sampling and Roots support are not mentioned. Overall, it’s a solid but basic MCP server implementation.

MCP Score