record_interaction
Save user and assistant messages to create continuous journaling sessions for tracking daily activities and conversation history.
Instructions
Record both the user's message and assistant's response.
Args: user_message: The user's message assistant_message: The assistant's response
Returns: str: Confirmation message
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"user_message": "<user_message>",
"assistant_message": "<assistant_message>"
},
"name": "record_interaction"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| user_message | Yes | ||
| assistant_message | Yes |
Implementation Reference
- server.py:140-167 (handler)The main handler function for the 'record_interaction' tool, decorated with @mcp.tool() for registration. It appends both user and assistant messages to the global conversation_log with timestamps and returns a confirmation.
@mcp.tool() async def record_interaction(user_message: str, assistant_message: str) -> str: """ Record both the user's message and assistant's response. Args: user_message: The user's message assistant_message: The assistant's response Returns: str: Confirmation message """ # Add user message first conversation_log.append({ "speaker": "user", "message": user_message, "timestamp": datetime.now().isoformat() }) # Then add assistant message conversation_log.append({ "speaker": "assistant", "message": assistant_message, "timestamp": datetime.now().isoformat() }) return "Conversation updated"