Merge pull request #10 from ferrislucas/cleanup

Additional REPL support

Author: ferrislucas

README.md

@@ -1,27 +1,40 @@
-![Main Image](.github/images/demo.gif)
-
 # iterm-mcp 
 A Model Context Protocol server that provides access to your iTerm session.
 
+![Main Image](.github/images/demo.gif)
+
 ### Features
 
-- **Efficient Token Use**: Only the visible content of the terminal is passed to the model. The model can retrieve content that's not visible if necessary.
-- **Supports Long-Running Processes**: iterm-mcp knows when the terminal is waiting for user input. Long-running processes are handled gracefully.
-- **Interrupt When Needed**: Send control characters to the terminal to interrupt processes.
-- **Inspect Terminal Activity**: Gives the model visibility into the current terminal content.
+**Efficient Token Use:** iterm-mcp gives the model the ability to inspect only the output that the model is interested in. The model typically only wants to see the last few lines of output even for long running commands. 
+
+**Natural Integration:** You share iTerm with the model. You can ask questions about what's on the screen, or delegate a task to the model and watch as it performs each step.
+
+**Full Terminal Control and REPL support:** The model can start and interact with REPL's as well as send control characters like ctrl-c, ctrl-z, etc.
+
+**Easy on the Dependencies:** iterm-mcp is built with minimal dependencies and is runnable via npx. It's designed to be easy to add to Claude Desktop and other MCP clients. It should just work.
+
 
 <a href="https://glama.ai/mcp/servers/h89lr05ty6"><img width="380" height="200" src="https://glama.ai/mcp/servers/h89lr05ty6/badge" alt="iTerm Server MCP server" /></a>
 
+## Safety Considerations
+
+* The user is responsible for using the tool safely.
+* No built-in restrictions: iterm-mcp makes no attempt to evaluate the safety of commands that are executed.
+* Models can behave in unexpected ways. The user is expected to monitor activity and abort when appropriate.
+* For multi-step tasks, you may need to interrupt the model if it goes off track. Start with smaller, focused tasks until you're familiar with how the model behaves. 
+
 ### Tools
-- `write_to_terminal` - Writes to the active iTerm terminal, often used to run a command.
-- `read_terminal_output` - Reads the output from the active iTerm terminal.
+- `write_to_terminal` - Writes to the active iTerm terminal, often used to run a command. Returns the number of lines of output produced by the command.
+- `read_terminal_output` - Reads the requested number of lines from the active iTerm terminal.
 - `send_control_character` - Sends a control character to the active iTerm terminal.
 
-## Installation
-
 ### Requirements
 
-- Node.js 18 or higher
+* iTerm2 must be running
+* Node version 18 or greater
+
+
+## Installation
 
 To use with Claude Desktop, add the server config:
 
@@ -74,7 +87,7 @@ Since MCP servers communicate over stdio, debugging can be challenging. We recom
 
 ```bash
 yarn run inspector
-yarn debug 
+yarn debug <command>
 ```
 
 The Inspector will provide a URL to access debugging tools in your browser.

src/ProcessTracker.ts

@@ -44,7 +44,10 @@ interface ActiveProcess {
 
 class ProcessTracker {
   private readonly shellNames = new Set(['bash', 'zsh', 'sh', 'fish', 'csh', 'tcsh']);
-  private readonly replNames = new Set(['irb', 'pry', 'rails', 'node', 'python', 'ipython']);
+  private readonly replNames = new Set([
+    'irb', 'pry', 'rails', 'node', 'python', 'ipython',
+    'scala', 'ghci', 'iex', 'lein', 'clj', 'julia', 'R', 'php', 'lua'
+  ]);
 
   /**
    * Get the active process and its resource usage in an iTerm tab
@@ -240,29 +243,28 @@ class ProcessTracker {
     let score = 0;
 
     // Base scores for process state
+    // 'R' (running) processes get 2 points, 'S' (sleeping) get 1 point
     score += process.state === 'R' ? 2 : process.state === 'S' ? 1 : 0;
 
     // CPU usage bonus
-    score += Math.min(process.cpuPercent / 10, 5); // Up to 5 points for CPU usage
+    // Add up to 5 points based on CPU usage percentage (1 point per 10%)
+    score += Math.min(process.cpuPercent / 10, 5);
 
     // Penalize shell processes unless they're the only option
+    // Shell processes are less interesting, so deduct 1 point
     if (this.shellNames.has(cmdName)) {
       score -= 1;
     }
 
     // Give high priority to REPL processes
-    if (cmd.includes('rails console') || 
-        cmd.includes('rails server') || 
-        this.replNames.has(cmdName)) {
+    // Add 3 points for REPLY processes
+    if (this.replNames.has(cmdName)) {
       score += 3;
     }
 
-    // Bonus for Ruby processes in a Rails context
-    if (cmdName === 'ruby' && cmd.includes('rails')) {
-      score += 2;
-    }
 
     // Bonus for active package manager operations
+    // Add 2 points for package managers like 'brew', 'npm', or 'yarn' if they are using CPU
     if ((cmdName === 'brew' || cmdName === 'npm' || cmdName === 'yarn') && 
         process.cpuPercent > 0) {
       score += 2;