Skip to main content
Glama
secemp9
by secemp9

kitty_launch

Create a new kitty window, tab, or OS window to run a command or shell, with configurable location, environment, and input source.

Instructions

Launch a new process in a kitty window, tab, or OS window. This is the primary window creation tool. Returns the ID of the newly created window. If no command is specified, the default shell is launched. Supports many launch options including window type, location, environment, and stdin source.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory. Special values: "current", "oldest", "last_reported", "root".
envNoEnvironment variables as "NAME=VALUE" strings. Example: ["TERM=xterm-256color", "DEBUG=1"].
varNoUser variables as "NAME=VALUE" strings, accessible via kitty match expressions.
holdNoKeep window open after the command exits.
selfNoUse the tab of the window this command runs in.
typeNoWhere to launch: window (in current tab), tab (new tab), os-window (new OS window), overlay (over current window), etc. Default: window.
matchNoTab match expression — which tab to create the window in.
copy_envNoCopy environment from the source window.
locationNoWhere in the tab to place the new window. "vsplit"/"hsplit" create vertical/horizontal splits. Default: default.
tab_titleNoTitle for the new tab (if launching in a new tab).
keep_focusNoKeep focus on the current window instead of switching.
copy_colorsNoCopy colors from the source window.
command_argsNoThe command and its arguments to run. Example: ["python3", "-m", "http.server", "8080"]. If omitted, the default shell is launched.
copy_cmdlineNoCopy command line from the source window.
stdin_sourceNoWhere to get stdin for the launched process.
window_titleNoTitle for the new window.
allow_remote_controlNoAllow remote control from the new window.
Behavior3/5

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

No annotations exist, so the description carries full burden. It discloses that the tool returns the newly created window ID and that omitting command_args launches the default shell. However, it does not mention side effects (e.g., resource usage, focus behavior if keep_focus not set) or permission requirements.

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?

The description is three sentences (though one is short) and front-loads the core purpose. It is efficient with no wasted words, but could be slightly more structured by grouping related info.

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 the tool's complexity (17 params, no output schema), the description is fairly complete: it explains the return value, default behavior, and key options. It could be enhanced by mentioning error handling or examples, but the rich schema compensates.

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

Parameters3/5

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

Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema, only highlighting that many launch options are supported and that no command defaults to shell. This does not significantly improve understanding of parameters.

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?

The description clearly states the tool launches a new process in a kitty window, tab, or OS window, and identifies itself as the 'primary window creation tool'. This verb+resource+scope is specific and distinguishes it from sibling tools like kitty_close_window or kitty_focus_window.

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

Usage Guidelines3/5

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

The description implies this is the go-to tool for creating windows, but does not explicitly mention when not to use it or provide alternatives. It mentions default shell behavior but lacks guidance like 'use kitty_run for quick commands' or 'use kitty_kitten for scripting'.

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/secemp9/kitty-mcp-server'

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