ItermSAFE
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A Model Context Protocol server that provides access to your iTerm session.
Features
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.
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. 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.
Requirements
- iTerm2 must be running
- Node version 18 or greater
Installation
To use with Claude Desktop, add the server config:
On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServerf9fe86161e92OBSERVED · 2026-09-29Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add iterm-mcp -- npx -y [email protected]
{
"mcpServers": {
"iterm-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (3)
1 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
read_terminal_output | read | Reads the output from the active iTerm terminal |
send_control_character | write | Sends a control character to the active iTerm terminal (e.g., Control-C, or special sequences like |
write_to_terminal | write | Writes text to the active iTerm terminal - often used to run a command in the terminal |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (6)
import CommandExecutor from '../../src/CommandExecutor.js';
import TtyOutputReader from '../../src/TtyOutputReader.js';
import SendControlCharacter from '../../src/SendControlCharacter.js';
jest.mock('../../src/TtyOutputReader.js', () => ({CommandExecutor = (await import('../../src/CommandExecutor.js')).default;@types/jest, @types/node, jest, jest-environment-node, ts-jest, ts-node, typescript
Gates applied: no_behavioural_pass.
f9fe86161e92full audit observations/trust-audit/mcp-server/ferrislucas__iterm.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-09-29 | f9fe86161e92 | SAFE | B | 89 | first audit |
Questions
What is the Iterm MCP server?
A Model Context Protocol server that executes commands in the current iTerm session - useful for REPL and CLI assistance
What tools does Iterm expose?
3 in total: 1 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Iterm safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Iterm need?
No credential environment variables were found in its source, so it appears to need none.
How does Iterm run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as iterm-mcp at 1.2.6.
How current is this page?
The grade is for one exact copy of the source (f9fe86161e92), read on 2026-09-29. The repository is watched and re-audited when it changes.