Every action below is available as an MCP tool and a verb in Cerebral OS — callable from any AI agent, Claude, Cursor, Windsurf, or your own runtime via the BYOA API. All executions are governed, audited, and dry-run safe.
Create Automation
harpa_ai:create_automation
Create a new automation with specified configuration.
Write
Medium risk
Create From Template
harpa_ai:create_from_template
Create a new automation based on an existing template with custom configuration.
Write
Medium risk
Delete Automation
harpa_ai:delete_automation
Permanently delete an automation. This action cannot be undone.
Write
High risk
Extract Data
harpa_ai:extract_data
Extract structured data from a web page using CSS selectors or XPath.
Write
Medium risk
Generate Content
harpa_ai:generate_content
Generate AI-powered content based on prompts and parameters.
Write
Medium risk
Get Automation
harpa_ai:get_automation
Fetch a single automation by ID with its configuration and status.
Read
Low risk
Get Execution
harpa_ai:get_execution
Fetch details of a specific automation execution including results and logs.
Read
Low risk
Get Template
harpa_ai:get_template
Fetch a specific automation template with its configuration and metadata.
Read
Low risk
List Automations
harpa_ai:list_automations
List automations with optional filtering and pagination.
Read
Low risk
List Executions
harpa_ai:list_executions
List automation executions with optional filtering and pagination.
Read
Low risk
List Templates
harpa_ai:list_templates
List available automation templates with filtering and search capabilities.
Read
Low risk
Run Automation
harpa_ai:run_automation
Execute an automation manually with optional parameters.
Write
Medium risk
Update Automation
harpa_ai:update_automation
Update an existing automation's configuration or settings.
Write
Medium risk