run_shell_command
-
Require one live configured pane, outside human-owned mode and running a supported POSIX foreground shell, then send one command and return output after its private completion boundary. The library’s literal-command checks do not read a command nested in a string tmux parses itself, such as an if-shell body. Run a shell command in a pane with your user’s permissions.
- MCP request method
tools/callSendrun_shell_commandas the tool name, with the arguments below.
Arguments#
-
Shell command sent to the pane.
- maxLength
1048576
-
Stable pane ID.
- maxLength
512
-
Completion timeout in milliseconds.
- minimum
1- maximum
60000
No other arguments are accepted.
Result#
Returns object
Annotations#
destructiveHinttrueidempotentHintfalseopenWorldHinttruereadOnlyHintfalsetitle"Run a shell command in a tmux pane"
Protocol data#
Use the complete advertised contract for validation and client integration.
Input schema
{"additionalProperties": false,"properties": {"command": {"description": "Shell command sent to the pane.","maxLength": 1048576,"type": "string"},"paneId": {"description": "Stable pane ID.","maxLength": 512,"type": "string"},"timeoutMs": {"description": "Completion timeout in milliseconds.","maximum": 60000,"minimum": 1,"type": "integer"}},"required": ["paneId","command"],"type": "object"}Output schema
{"additionalProperties": true,"type": "object"}