iTerm MCP

MCP server that lets AI models execute commands in an active iTerm2 terminal session. Provides tools to write commands, read output lines selectively for token efficiency, and send control characters (Ctrl+C, Ctrl+Z). User and AI share the same terminal window for real-time collaboration.

Evaluated Mar 06, 2026 (0d ago) v1.2.6
Homepage ↗ Repo ↗ Developer Tools mcp iterm2 terminal cli macos repl shell command-execution
⚙ Agent Friendliness
63
/ 100
Can an agent use this?
🔒 Security
70
/ 100
Is it safe for agents?
⚡ Reliability
64
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
65
Documentation
65
Error Messages
45
Auth Simplicity
68
Rate Limits
55

🔒 Security

TLS Enforcement
80
Auth Strength
75
Scope Granularity
60
Dep. Hygiene
70
Secret Handling
65

Community/specialized tool. Apply standard security practices for category. Review documentation for specific security requirements.

⚡ Reliability

Uptime/SLA
70
Version Stability
65
Breaking Changes
60
Error Recovery
60
AF Security Reliability

Best When

You are on macOS using iTerm2 and want an AI assistant to directly execute commands, read output, and interact with REPLs in your terminal session with full visibility.

Avoid When

You need cross-platform terminal support, want built-in safety restrictions on command execution, or are running in a headless environment without iTerm2.

Use Cases

  • • AI-assisted CLI workflows where the model runs commands and reads output in your iTerm session
  • • REPL-driven development with AI executing and iterating on code in interactive shells
  • • Debugging terminal-based applications with AI reading and analyzing output
  • • Automating multi-step terminal operations with AI oversight
  • • Pair programming in the terminal where both human and AI can observe and act

Not For

  • • Non-macOS platforms (requires iTerm2)
  • • Headless or remote server environments without iTerm2
  • • Production automation or CI/CD pipelines
  • • Sandboxed or restricted execution environments needing safety guardrails

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

No authentication required. Operates within the user's existing iTerm2 session context via AppleScript integration.

Pricing

Model: open_source
Free tier: Yes
Requires CC: No

Fully open source under MIT license.

Agent Metadata

Pagination
offset
Idempotent
No
Retry Guidance
Not documented

Known Gotchas

  • ⚠ No built-in safety restrictions - model has full command execution capability
  • ⚠ macOS-only due to iTerm2 and AppleScript dependency
  • ⚠ Models may execute destructive commands unpredictably - user must monitor
  • ⚠ Shared terminal means user and AI commands can interleave unpredictably
  • ⚠ Control characters (Ctrl+C) may not behave as expected in all REPL contexts

Alternatives

terminal-mcp-server shell-mcp

Full Evaluation Report

Detailed scoring breakdown, competitive positioning, security analysis, and improvement recommendations for iTerm MCP.

$99
API endpoint ↗ Agent guide ↗ Report inaccuracy

Scores are editorial opinions as of 2026-03-06.

5215
Packages Evaluated
26151
Need Evaluation
173
Need Re-evaluation
♥
Community Powered