store_memory
Stores a new piece of information, such as an insight or a solution.
How to use it
store_memory is exposed by the Heimdall MCP Server MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the store_memory tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Heimdall MCP Server
$
pip install heimdall-mcpOther tools in Heimdall MCP Server (5)
delete_memories_by_tags
Delete all memories that have any of the specified tags.
delete_memory
Delete a specific memory by its unique ID.
memory_status
Checks the health and statistics of the memory system.
recall_memories
Performs a semantic search for relevant memories based on a query.
session_lessons
Records a key takeaway from the current session for future use.