Skip to main content
Glama

send_control

Send control signals (e.g., Ctrl+C, arrow keys) to running commands in local terminals or SSH sessions. Use to interrupt stuck processes or interact with TUI apps like vim or tmux.

Instructions

Send a control key/signal to a running command. Use this whenever a
raw control byte or escape sequence is needed — interrupting a stuck
command OR driving a TUI (zellij, vim, less, htop, etc.). Prefer this
over `respond` for non-printable input: many AI frameworks strip
control characters from MCP string arguments, but the string-keyed
enum here is always safe.

Signal names are case-insensitive. Supported values:

  ctrl+a .. ctrl+z              0x01..0x1A (e.g. ctrl+o for zellij detach)
  ctrl+\, ctrl+], ctrl+^, ctrl+_, ctrl+[
  esc, tab, enter, return, space, backspace, bs
  up, down, left, right
  home, end, pageup, pagedown, insert, delete, del
  backtab / shift+tab
  f1 .. f12
  alt+<char>                    ESC + char (bash readline, emacs)

Local non-PTY subprocesses only react to ctrl+c, ctrl+z, ctrl+\
(mapped to SIGINT/SIGTSTP/SIGQUIT). SSH and PTY channels accept all
of the above as raw bytes / escape sequences.

Returns the same format as execute/respond.

Args:
- pause_timeout: seconds of output silence after sending the key
  before returning (default 9.0). Raise this if the key is expected
  to trigger slow output (e.g. a TUI repaint over high-latency SSH).
- total_timeout: hard cap on call duration (default 20.0). Only binds
  while output is actively streaming.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
command_idYesThe active command_id returned in a partial status response
signalNoThe control signal or key to send. Supported values: 'ctrl+c', 'ctrl+z', 'ctrl+d', arrow keys, enter, f1-f12, etc.ctrl+c
pause_timeoutNoSeconds of output silence to wait before returning (default is 9.0)
total_timeoutNoHard cap in seconds on the maximum duration of this call (default is 20.0)
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description details case-insensitive signals, supported values, local vs PTY differences, and timeout behaviors. Does not explicitly mention destructive potential but implies via SIGINT/SIGTSTP. No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with purpose first, then usage, then comprehensive signal list. Slightly long but every sentence adds value. Good front-loading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations or output schema, description covers purpose, behavior, parameters, and return format reference. Sufficient for agent to use correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline 3. Description adds value by expanding signal list with examples, case-insensitivity, and timeout explanations, going beyond schema defaults.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Send a control key/signal to a running command' and distinguishes from 'respond' for non-printable input. Specific verb+resource with use cases (interrupting stuck command, driving TUI).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises when to use (non-printable input) and when not (printable input - prefer respond). Also notes local subprocess limitations vs SSH/PTY.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/QiuwenZheng/interminal'

If you have feedback or need assistance with the MCP directory API, please join our Discord server