Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| system_prompt_for_agent | Generates a system prompt for an AWS cost analysis agent. This function creates a specialized prompt for an AI agent that analyzes AWS cloud spending. The prompt instructs the agent on how to retrieve, analyze, and present cost optimization insights for AWS accounts. Args: aws_account_id (Optional[str]): The AWS account ID to analyze. If provided, the agent will focus on this specific account. If None, the agent will function without account-specific context. Returns: str: A formatted system prompt for the AWS cost analysis agent. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| config://app |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_bedrock_daily_usage_stats | Get daily usage statistics with detailed breakdowns.
Args:
params: Parameters specifying the number of days to look back and region
Returns:
str: Formatted string representation of daily usage statistics |
| get_bedrock_hourly_usage_stats | Get hourly usage statistics with detailed breakdowns.
Args:
params: Parameters specifying the number of days to look back and region
Returns:
str: Formatted string representation of hourly usage statistics |
| get_ec2_spend_last_day | Retrieve EC2 spend for the last day using standard AWS Cost Explorer API.
Returns:
Dict[str, Any]: The raw response from the AWS Cost Explorer API, or None if an error occurs. |
| get_detailed_breakdown_by_day | Retrieve daily spend breakdown by region, service, and instance type.
Args:
params: Parameters specifying the number of days to look back
Returns:
Dict[str, Any]: A tuple containing:
- A nested dictionary with cost data organized by date, region, and service
- A string containing the formatted output report
or (None, error_message) if an error occurs. |