app.launch
Launch an executable on the remote Windows rig (name on PATH or absolute path), optional args. Side effects: starts a process; Glasswarp tracks it and closes it on session.end. Use for notepad.exe, mspaint.exe, chrome with URL args, etc. Wait/re-observe after launch before clicking — do not assum...
This record as markdown: /tools/com-glasswarp-mcp-server/app.launch.md
What app.launch does on Glasswarp
AI agents invoke app.launch to trigger actions in Glasswarp. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
args | array | — | Process args, e.g. ["--new-window", "https://example.com"] |
session_id | string | Yes | Active session id |
path_or_name | string | Yes | Executable name (e.g. notepad.exe) or absolute path |
Parameters from the server's own tool schema.
Why app.launch is rated High
app.launch triggers external process execution on a remote Windows machine with effects determined by the executable and arguments provided. This is a classic Execute pattern — the tool itself runs code/operations whose consequences depend on what is launched.
From the tool's definition Tool description explicitly states 'Launch an executable on the remote Windows rig' and 'starts a process', clearly indicating code/process execution capability. The tool accepts arbitrary executables by 'name on PATH or absolute path' with optional arguments.
Attacks that exploit this kind of access
The rule that runs app.launch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Glasswarp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For app.launch, this is the rule to start with:
app.launch stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Glasswarp, apply this rule, and every app.launch call is checked against it from then on.
Questions about app.launch
Launch an executable on the remote Windows rig (name on PATH or absolute path), optional args. Side effects: starts a process; Glasswarp tracks it and closes it on session.end. Use for notepad.exe, mspaint.exe, chrome with URL args, etc. Wait/re-observe after launch before clicking — do not assume the window is focused immediately. It is categorised as a Execute tool in the Glasswarp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
app.launch accepts 3 parameters: args, session_id, path_or_name. Required: session_id, path_or_name. The full parameter table on this page comes from the server's own tool schema.
Register the Glasswarp MCP server in PolicyLayer and add a rule for app.launch: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Glasswarp. Nothing to install.
app.launch is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the app.launch rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for app.launch. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
app.launch is provided by the Glasswarp MCP server (https://mcp.glasswarp.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Glasswarp, and thousands of servers like it.
Across the catalogue