Hermes - Automated Asynchronous REST API Monitoring

by agents-mcp-hackathonco.huggingface.agents-mcp-hackathon/hermes

  • Remote endpoint
  • 3 tools
  • MIT

Tools

  • hermes_activate_monitoring TOOL: Activate periodic monitoring for a validated API configuration. PURPOSE: Start automated recurring API calls based on a previously validated configuration. This is STEP 2 of the monitoring setup process. PREREQUISITE: Must call validate_api_configuration() first and obtain a config_id from successful validation. Make sure that the sample_response is what you expect to see before proceeding with this function. WORKFLOW: 1. First call validate_api_configuration() to get config_id 2. If validation successful, call this function with the config_id 3. Monitoring will run automatically according to the validated schedule ARGUMENTS: - config_id: The ID from successful validate_api_configuration() execution (required) - mcp_api_key: User's MCP API key for verification (must match validation step). Input Examples: 1. Activate scheduler for stock monitoring: config_id: 123456789 mcp_api_key: "your_mcp_key_here" 2. Activate scheduler for weather alerts: config_id: 987654321 mcp_api_key: "yo
  • hermes_retrieve_monitored_data TOOL: Retrieve monitored data for a specific API configuration. PURPOSE: Fetch the latest monitored data for a given configuration ID. This is STEP 3 of the monitoring setup process. PREREQUISITE: Must call validate_api_configuration() first and obtain a config_id from successful validation, then activate_monitoring() to start monitoring. This function can be called at any time after monitoring activation to retrieve the latest data collected by the monitoring system. ARGUMENTS: - config_id: The ID of the API configuration to retrieve data for (required) - mcp_api_key: User's MCP API key for verification (must match validation step). - mode: Data return mode - "summary" (LLM-optimized), "details" (full responses, minimal metadata), "full" (everything) Input Examples: 1. Retrieve data for stock monitoring: config_id: 123456789 mcp_api_key: "your_mcp_key_here" 2. Retrieve data for weather alerts: config_id: 987654321 mcp_api_key: "your_mcp_key_here". Returns: Dictionary with monitoring s
  • hermes_validate_api_configuration TOOL: Validate and store API configuration for monitoring. PURPOSE: Test an API endpoint and store the configuration if successful. This is STEP 1 of the monitoring setup process. If validation fails, retry with corrected parameters. If successful, use the returned config_id in activate_monitoring() function. CRITICAL: Even if success=True, you MUST manually check the 'sample_response' field before proceeding to activate_monitoring(). The API call may return success=True but contain error messages (like "401 Unauthorized", "Invalid API key", etc.) in the sample_response. CRITICAL: Always try to add parameters that will limit the API response to a manageable size. CRITICAL: Be sure to always clearly inform the user of the config_id after a desired validation result. CRITICAL: If you don't have an MCP API KEY given by the user, prompt them to get it here: https://mcp-hackathon.vercel.app/ WORKFLOW: 1. Call this function to validate API configuration 2. If success=False: Fix parameters

As the server's own listing gives them. We never call a tool.