Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| implore | This tool launches a separate GUI process to show a quiz with one or more questions and waits for the user to respond. Multiple choice questions include an automatic "Other..." option with text input for additional flexibility. Perfect for clarifying requirements, getting decisions, or extracting implicit knowledge from users. Args: questions: A list of question objects. Each question object should have: - text (str): The question text - type (str): Either "multiple_choice" or "free_form". For "multiple_choice", an automatic "Other..." radio button with text input is included after the options. - options (list, optional): List of options for multiple choice questions - id (str, optional): Unique identifier (auto-generated as "q1", "q2", etc. if not provided) title: The title of the dialog window (default: "Human Input Requested") Returns: Dictionary with structured response: - On success: {"success": True, "answers": {question_id: answer, ...}} - On cancel: {"success": False, "cancelled": True} - On error: {"success": False, "error": "error message"} Notes:
Examples: Single question: implore(questions=[ { "id": "api_key", "text": "What is your API key?", "type": "free_form" } ]) Multiple questions:
implore(questions=[
{
"id": "framework",
"text": "Which framework should we use?",
"type": "multiple_choice",
"options": ["React", "Vue", "Angular"]
},
{
"id": "requirements",
"text": "Any additional requirements?",
"type": "free_form"
}
]) |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |