get_user_memory_buckets
List all memory buckets (AI profiles) for the authenticated user.
Each bucket is a themed collection of documents, notes, and files.
Returns bucket IDs, names, and item counts.
Use this first to discover available memory buckets before browsing
or searching their contents.
Returns both owned buckets and buckets shared with the user.
Each bucket has a `role` ('owner', 'editor', or 'viewer') and
shared buckets include `sharedBy` information.
list_items_in_memory_bucket
List all stored items (documents, files, notes) inside a specific memory bucket.
Returns item metadata including title, description, source type, file name,
size, and chunk count — but not the actual content.
Use this to browse what's stored in a bucket before reading or searching
specific items.
Args:
profile_id: The ID of the memory bucket (profile) to list items from.
search_memory
Search across the user's stored memory using semantic vector similarity.
Finds relevant content even when the query doesn't exactly match stored text.
Searches all memory buckets by default, or specify bucket IDs to narrow scope.
Searches across both owned and shared buckets automatically.
Returns results grouped by memory bucket and context, with content previews
and relevance scores.
Use this to discover which contexts contain relevant information,
then use read_context to get the full content.
Args:
query: The search query to find relevant memories.
profile_ids: Optional list of memory bucket IDs to search within.
If not provided, searches across all buckets.
k: Number of results to return (default: 5).
read_context
Read the full content of a specific stored memory item (document, file, or note).
Returns the actual text content with pagination support for large documents.
Use start_chunk and limit to read specific portions — defaults to returning
all content.
Use this after finding an item via list_items_in_memory_bucket or search_memory.
Args:
context_id: The ID of the context/item to read.
start_chunk: Chunk index to start reading from (default: 0).
limit: Maximum number of chunks to return (default: 0 = all chunks).
save_memory
Save text content to a specific memory bucket.
IMPORTANT — Before calling this tool:
1. Call get_user_memory_buckets to list available buckets
2. Ask the user which bucket to save to, or offer to create a new one
3. If the user wants a new bucket, call create_memory_bucket first
Args:
profile_id: The ID of the memory bucket to save to (required).
content: The text content to save.
title: Optional custom title for this memory. If not provided, a title
is generated automatically from the content.
source_platform: The name of this MCP client platform
(e.g. "claude", "chatgpt", "cursor").
save_conversation
Save a conversation (chat history) to a specific memory bucket.
IMPORTANT — Before calling this tool:
1. Call get_user_memory_buckets to list available buckets
2. Ask the user which bucket to save to, or offer to create a new one
3. If the user wants a new bucket, call create_memory_bucket first
Args:
profile_id: The ID of the memory bucket to save to (required).
chat_history: List of chat messages, each with 'role' ("user" or "assistant")
and 'content' (the message text).
title: Optional custom title for this conversation. If not provided, a title
is generated automatically from the conversation content.
source_platform: The name of this MCP client platform
(e.g. "claude", "chatgpt", "cursor").