reasoning
(string, optional): Reasoning behind the decision
How to use it
reasoning is exposed by the Cursor10x MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the reasoning tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
FULL CURSOR10X MCP LISTINGOther tools in Cursor10x MCP (36)
(string, required): Action performed on the file (open, edit, close, etc.)
(string, required): Actor performing the action (user, assistant, system)
(string, required): Content of the user message
(number, optional): ID of the content this vector represents (for store, update, delete)
(string, optional): Type of content ("message", "file", "snippet", etc.)
(string, optional): Context for the episode
(string, required): Description of the milestone
Contains the banner to be shown to the user
(string, required): Path to the file being tracked
(string, optional): Importance level ("low", "medium", "high", "critical"), defaults to "low"
Contains the comprehensive context for the agent's use
(number, optional): Maximum number of messages to retrieve, defaults to 10
Checks the health of the memory system and its database connection.
Ends a conversation by combining multiple operations in one call: storing the assistant's final message, recording a milestone for what was accomplished, and logging an episode in the episodic memory. This unified tool replaces the need for separate storeAssistantMessage, storeMilestone, and recordE
Retrieves active files from the short-term memory.
Retrieves a unified context from all memory subsystems, combining short-term, long-term, and episodic memory.
Retrieves detailed statistics about the memory system.
Retrieves recent episodes from the episodic memory.
Retrieves recent messages from the short-term memory.
Initializes a conversation by storing the user message, generating a banner, and retrieving context in one operation. This unified tool replaces the need for separate generateBanner, getComprehensiveContext, and storeUserMessage calls at the beginning of each conversation.
Unified tool for managing vector embeddings with operations for store, search, update, and delete.
Records an episode (action) in the episodic memory.
Stores an assistant message in the short-term memory system.
Stores a project decision in the long-term memory.
Stores a project milestone in the long-term memory.
Stores a project requirement in the long-term memory.
Stores a user message in the short-term memory system.
Tracks an active file being accessed or modified by the user.
(object, optional): Additional metadata for the message
(string, required): Description of what was accomplished
(string, required): Title of the milestone to record
(string, required): Operation to perform ("store", "search", "update", "delete")
(number, optional): Similarity threshold for search operation, defaults to 0.7
(string, required): Title of the milestone
(array, optional): Vector data as array of numbers (for store, update) or query vector (for search)
(number, optional): ID of the vector to update or delete