Skip to main content
Glama

restart_llm_server

Restart the LLM server running on a given port, optionally switching to a different model.

Instructions

指定されたポートで稼働しているサーバーを一度停止し、再起動します。モデルの切り替えなどにも使用できます。

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
portYes再起動するサーバーのポート番号
model_nameNo(オプション)新しく起動するモデル名。省略した場合は現在そのポートで稼働しているモデルをそのまま再起動します。
memory_requirement_gbNo(オプション)起動に必要な空きメモリの目安(GB)。未指定時はデフォルトで 4.0GB。

Implementation Reference

  • Handler for restart_llm_server tool. Validates arguments (port integer, optional model_name string, optional memory_requirement_gb number) then calls process_manager.restart_server() via asyncio.to_thread.
    elif name == "restart_llm_server":
        port = arguments.get("port")
        model_name = arguments.get("model_name")
        memory_requirement_gb = arguments.get("memory_requirement_gb", 4.0)
        
        if not isinstance(port, int):
            raise ValueError("Port must be an integer")
        if model_name is not None and not isinstance(model_name, str):
            raise ValueError("model_name must be a string")
        if not isinstance(memory_requirement_gb, (int, float)):
            raise ValueError("memory_requirement_gb must be a number")
            
        result_msg = await asyncio.to_thread(
            process_manager.restart_server, 
            port,
            model_name,
            10, 
            float(memory_requirement_gb)
        )
        return [types.TextContent(type="text", text=result_msg)]
  • MlxProcessManager.restart_server() method. Loads state, checks if port exists, optionally switches model name, calls shutdown_server(), waits 1s for OS port release, then calls launch_server() with the target model.
    def restart_server(self, port: int, model_name: str = None, timeout: int = 10, memory_requirement_gb: float = 4.0) -> str:
        """指定されたポートのサーバーを再起動する"""
        state = self._load_state()
        port_str = str(port)
    
        if port_str not in state:
            return f"Error: No running server found on port {port} to restart."
    
        # モデル名が指定されていない場合は、現在のモデルを引き継ぐ
        current_model = state[port_str].get("model", "unknown")
        target_model = model_name if model_name else current_model
    
        if target_model == "unknown":
            return "Error: Cannot determine the current model to restart. Please specify model_name explicitly."
    
        shutdown_msg = self.shutdown_server(port)
        if "Error" in shutdown_msg:
            return f"Failed to shutdown existing server: {shutdown_msg}"
    
        # OSがポートを完全に解放するまで少し待機
        time.sleep(1)
    
        launch_msg = self.launch_server(target_model, port, timeout, memory_requirement_gb)
        return f"{shutdown_msg}\nRestart Result: {launch_msg}"
  • Tool registration with inputSchema. Defines 'restart_llm_server' with required 'port' (integer), optional 'model_name' (string), optional 'memory_requirement_gb' (number).
    types.Tool(
        name="restart_llm_server",
        description="指定されたポートで稼働しているサーバーを一度停止し、再起動します。モデルの切り替えなどにも使用できます。",
        inputSchema={
            "type": "object",
            "properties": {
                "port": {"type": "integer", "description": "再起動するサーバーのポート番号"},
                "model_name": {
                    "type": "string",
                    "description": "(オプション)新しく起動するモデル名。省略した場合は現在そのポートで稼働しているモデルをそのまま再起動します。"
                },
                "memory_requirement_gb": {
                    "type": "number",
                    "description": "(オプション)起動に必要な空きメモリの目安(GB)。未指定時はデフォルトで 4.0GB。"
                }
            },
            "required": ["port"],
        },
    ),
  • Tool registration via @server.list_tools() decorator. The list includes 'restart_llm_server' at lines 98-116 within the handle_list_tools function.
    @server.list_tools()
    async def handle_list_tools() -> list[types.Tool]:
        """AIエージェントに提供するツールの一覧とスキーマを定義します"""
        return [
            types.Tool(
                name="check_system_environment",
                description="現在のシステム環境(Apple Siliconか、空きメモリが何GBあるかなど)を診断します。",
                inputSchema={
                    "type": "object",
                    "properties": {},
                },
            ),
            types.Tool(
                name="check_llm_status",
                description="指定されたポートでサーバーがリッスンしているか(稼働中か)を確認します。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "port": {"type": "integer", "description": "確認するポート番号"}
                    },
                    "required": ["port"],
                },
            ),
            types.Tool(
                name="list_running_servers",
                description="現在バックグラウンドで稼働しているすべてのローカルLLMサーバー(ポート番号とモデル名)の一覧を取得します。",
                inputSchema={
                    "type": "object",
                    "properties": {},
                },
            ),
            types.Tool(
                name="search_mlx_models",
                description="Hugging Faceからダウンロード可能なMLXフォーマットのLLMモデルを検索・リストアップします。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "search_query": {
                            "type": "string",
                            "description": "検索キーワード(例: 'llama', 'qwen')。未指定の場合は人気のMLXモデルを返します。"
                        },
                        "limit": {
                            "type": "integer",
                            "description": "取得する最大件数。デフォルトは10。"
                        }
                    },
                },
            ),
            types.Tool(
                name="download_model",
                description="Hugging Faceから指定されたMLXモデルを事前にダウンロードし、ローカルにキャッシュします。大きなモデルの起動前の準備に利用します。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "model_name": {
                            "type": "string",
                            "description": "ダウンロードするモデル名 (例: mlx-community/Llama-3-8B-Instruct-4bit)"
                        }
                    },
                    "required": ["model_name"],
                },
            ),
            types.Tool(
                name="launch_llm_server",
                description="mlx_lm.server をサブプロセスとしてバックグラウンドで起動します。空きメモリが少ない場合は起動が拒否されます。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "model_name": {
                            "type": "string",
                            "description": "起動するモデル名 (例: mlx-community/Llama-3-8B-Instruct-4bit)",
                        },
                        "port": {"type": "integer", "description": "サーバーを起動するポート番号"},
                        "memory_requirement_gb": {
                            "type": "number",
                            "description": "起動に必要な空きメモリの目安(GB)。未指定時はデフォルトで 4.0GB。"
                        }
                    },
                    "required": ["model_name", "port"],
                },
            ),
            types.Tool(
                name="restart_llm_server",
                description="指定されたポートで稼働しているサーバーを一度停止し、再起動します。モデルの切り替えなどにも使用できます。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "port": {"type": "integer", "description": "再起動するサーバーのポート番号"},
                        "model_name": {
                            "type": "string",
                            "description": "(オプション)新しく起動するモデル名。省略した場合は現在そのポートで稼働しているモデルをそのまま再起動します。"
                        },
                        "memory_requirement_gb": {
                            "type": "number",
                            "description": "(オプション)起動に必要な空きメモリの目安(GB)。未指定時はデフォルトで 4.0GB。"
                        }
                    },
                    "required": ["port"],
                },
            ),
            types.Tool(
                name="shutdown_llm_server",
                description="指定されたポートで稼働しているローカル LLM サーバープロセスを安全に終了させます。",
                inputSchema={
                    "type": "object",
                    "properties": {
                        "port": {"type": "integer", "description": "終了させるサーバーのポート番号"}
                    },
                    "required": ["port"],
                },
            ),
        ]
Behavior2/5

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

No annotations are provided, and the description does not disclose behavioral traits such as service disruption, session handling, or error states. For a destructive operation, this is insufficient.

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 a single concise sentence that gets to the point. However, it could be more informative without being verbose.

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

Completeness2/5

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

Given the lack of output schema and annotations, the description should provide more context about what happens during restart, prerequisites (e.g., server must be running), and potential impacts. It falls short.

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?

Input schema covers 100% of parameters with clear descriptions. The tool's description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.

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 that it stops and restarts a server on a specified port, and mentions it can be used for switching models. This aligns with the name and distinguishes it from siblings like 'shutdown_llm_server' and 'launch_llm_server'.

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 usage for model switching but does not explicitly state when to use versus alternatives. No guidance on when not to use or prerequisites.

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/globalpocket/mcp-mlx-launcher'

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