smart-terminal-mcp 1.2.4 → 1.2.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -6,16 +6,20 @@ Unlike simple `exec`-based approaches, this provides full PTY sessions with bidi
|
|
|
6
6
|
|
|
7
7
|
## Why use this instead of your AI client's built-in terminal?
|
|
8
8
|
|
|
9
|
-
Install this if you want
|
|
9
|
+
Install this if you want a more consistent terminal workflow across different AI clients, not just whatever built-in terminal behavior one client happens to provide.
|
|
10
10
|
|
|
11
11
|
This MCP is most useful when you want:
|
|
12
12
|
|
|
13
|
+
- **The same workflow across multiple agent platforms** -- If you move between Claude Code, Cursor, Trae, Antigravity, or other MCP-capable clients, the terminal tools stay the same.
|
|
14
|
+
- **Less client-specific behavior** -- Prompts, instructions, and habits do not need to depend as much on one client's terminal UI or quirks.
|
|
15
|
+
- **Reusable prompts, playbooks, and instructions** -- A workflow built around tools like `terminal_wait`, `terminal_retry`, `terminal_run_paged`, or `terminal_get_history` is easier to reuse across teams and clients.
|
|
16
|
+
- **Reusable tooling with less lock-in** -- The terminal layer lives in MCP tools rather than in one client's built-in terminal behavior.
|
|
13
17
|
- **Persistent terminal state** -- Keep the same shell session alive across steps, including the current folder, environment, and running processes.
|
|
14
18
|
- **Better interactive behavior** -- Handle prompts, REPLs, dev servers, Ctrl+C, arrow keys, and other real terminal interactions.
|
|
15
19
|
- **More control over large output** -- Truncate, page, diff, retry, wait for patterns, or fetch history instead of dumping everything at once.
|
|
16
20
|
- **More predictable automation** -- Use deterministic completion markers instead of guessing when a command is done.
|
|
17
21
|
|
|
18
|
-
If your AI client already gives you a stable, stateful, interactive terminal with good output handling, you may not need this MCP.
|
|
22
|
+
If your AI client already gives you a stable, stateful, interactive terminal with good output handling, you may not need this MCP for basic command execution. The main reason to add it is to make terminal-driven workflows more explicit, reusable, and portable across clients.
|
|
19
23
|
|
|
20
24
|
## Features
|
|
21
25
|
|