Two modes depending on whether session_id is provided:

Without session_id (permanent memory): Runs the full add + cognify
pipeline to ingest data and build the knowledge graph.

With session_id (session memory): Stores the data in the session
cache only. Fast, no entity extraction. Omit session_id when the
content should be stored as permanent graph memory.

Parameters
----------
data : str
    The data to store (text content).
dataset_name : str, optional
    Target dataset name. Defaults to the current MCP client's
    agent-scoped dataset (e.g. "cursor_vscode_memory"), or
    "main_dataset" if no client identity is detected.
session_id : str, optional
    Session ID. When set, stores in session cache only.
custom_prompt : str, optional
    Custom prompt for entity extraction (permanent mode only).

When session_id is provided without datasets or search_type,
searches session cache first by keyword matching. Falls through
to the permanent knowledge graph if no session results match.

Auto-routing picks the best search strategy when search_type
is not specified.

Parameters
----------
query : str
    Natural language query to search for.
search_type : str, optional
    Override auto-routing. Options: GRAPH_COMPLETION,
    GRAPH_COMPLETION_COT, RAG_COMPLETION, CHUNKS, SUMMARIES,
    TEMPORAL, FEELING_LUCKY, etc.
datasets : str, optional
    Comma-separated dataset names to search within.
session_id : str, optional
    Session ID for session-first search.
top_k : int
    Maximum results to return (default: 10).

Can target a specific dataset or delete everything the user owns.
Removes data from the relational DB, graph DB, and vector DB.

Parameters
----------
dataset : str, optional
    Dataset name to delete entirely.
everything : bool
    If true, delete ALL data across all datasets.