Start a LangGraph server and return a connected remote agent client.
start_server_and_get_agent(
*,
assistant_id: str,
model_name: str | None = None,
model_params: dict[str, Any] | None = None,
auto_approve: bool = False,
sandbox_type: str = 'none',
sandbox_id: str | None = None,
sandbox_setup: str | None = None,
enable_shell: bool = True,
enable_ask_user: bool = False,
mcp_config_path: str | None = None,
no_mcp: bool = False,
trust_project_mcp: bool | None = None,
interactive: bool = True,
host: str = '127.0.0.1',
port: int = 2024
) -> tuple[RemoteAgent, ServerProcess, MCPSessionManager | None]| Name | Type | Description |
|---|---|---|
assistant_id* | str | Agent identifier. |
model_name | str | None | Default: NoneModel spec string. |
model_params | dict[str, Any] | None | Default: NoneExtra model kwargs. |
auto_approve | bool | Default: FalseAuto-approve all tools. |
sandbox_type | str | Default: 'none'Sandbox type. |
sandbox_id | str | None | Default: NoneExisting sandbox ID to reuse. |
sandbox_setup | str | None | Default: NonePath to setup script for the sandbox. |
enable_shell | bool | Default: TrueEnable shell execution tools. |
enable_ask_user | bool | Default: FalseEnable ask_user tool. |
mcp_config_path | str | None | Default: NonePath to MCP config. |
no_mcp | bool | Default: FalseDisable MCP. |
trust_project_mcp | bool | None | Default: NoneTrust project MCP servers. |
interactive | bool | Default: TrueWhether the agent is interactive. |
host | str | Default: '127.0.0.1'Server host. |
port | int | Default: 2024Server port. |