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.
Add Data Source
chat_data:add_data_source
Add a new data source to train a chatbot with additional knowledge.
Write
Medium risk
Create Chatbot
chat_data:create_chatbot
Create a new chatbot with specified configuration.
Write
Medium risk
Delete Chatbot
chat_data:delete_chatbot
Permanently delete a chatbot and all its data sources. This action cannot be undone.
Write
High risk
Delete Data Source
chat_data:delete_data_source
Permanently delete a data source from a chatbot. This will remove the training data and cannot be undone.
Write
High risk
Get Chatbot
chat_data:get_chatbot
Fetch a single chatbot by ID with configuration and training status.
Read
Low risk
Get Conversation
chat_data:get_conversation
Retrieve a conversation with all messages between user and chatbot.
Read
Low risk
List Chatbots
chat_data:list_chatbots
List all chatbots with optional filtering and pagination.
Read
Low risk
List Conversations
chat_data:list_conversations
List conversations with optional filtering and pagination.
Read
Low risk
List Data Sources
chat_data:list_data_sources
List all data sources for a specific chatbot with optional filtering.
Read
Low risk
Retrain Chatbot
chat_data:retrain_chatbot
Trigger retraining of a chatbot with all its current data sources.
Write
Medium risk
Send Message
chat_data:send_message
Send a message to a chatbot and get an AI response.
Write
Medium risk
Update Chatbot
chat_data:update_chatbot
Update an existing chatbot's configuration.
Write
Medium risk