Skip to main content
Glama

mc_quit_client

Shuts down the Minecraft client gracefully and waits for complete exit, enabling safe immediate relaunch. For development loops requiring clean client termination.

Instructions

Gracefully shut down the entire Minecraft client. This tears down the user's whole play session, including any world or server they're in — only do it when asked, or as part of a dev loop the user set up (typically the quit step of build → deploy → quit → launch → mc_wait_for_bridge; see the mcdev://guides/dev-loop resource).

Fire-and-acknowledge: the WebSocket is expected to drop moments after the ack (that counts as success). By default the tool then waits for the client to be truly gone: it resolves the PID listening on the bridge port before quitting, polls until the port stops listening, then until that process exits — so on success it's safe to relaunch immediately, even through launchers that track the instance (Prism silently ignores --launch while the old process lives). When the PID can't be resolved (no lsof, permissions), it falls back to port-close-only and the result says so — the JVM can outlive the port by a few seconds, so in that case confirm the process exited yourself (pgrep / kill -0) before relaunching. Requires session_control_enabled=true in the DebugBridge config.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitForExitNoWait until the client is actually gone — bridge port closed, then the client process exited (when its PID could be resolved) — before returning. Default true.
timeoutSecondsNoHow long to wait for the whole shutdown (port close + process exit). Default 30.
Behavior5/5

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

With no annotations provided, the description fully covers behavioral traits: the graceful shutdown process, fire-and-acknowledge mechanism, wait fallbacks, PID resolution, and requirement for session_control_enabled=true.

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

Conciseness5/5

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

The description is concise yet comprehensive, with the core purpose front-loaded and all necessary details included without redundancy.

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

Completeness5/5

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

Given no output schema and two parameters, the description is complete: it covers shutdown process, wait behavior, fallbacks, requirements, and references a guide for deeper context.

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

Parameters5/5

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

The description adds significant meaning beyond the schema by explaining the wait mechanism, fallback behavior, and recommendations when PID cannot be resolved, enhancing the schema's basic descriptions.

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's purpose: 'Gracefully shut down the entire Minecraft client.' This distinguishes it from siblings like mc_leave_server, which only leaves a server without quitting the client.

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

Usage Guidelines4/5

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

The description provides explicit usage context: 'only do it when asked, or as part of a dev loop...' and references a guide. It implies not to use it casually but does not explicitly name alternatives like mc_leave_server.

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/use-ai-for-mc/mcdev-mcp'

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