cursor10x-mcp

Overview

DevContext creates a persistent memory layer for AI assistants, enabling them to retain and recall conversation history, project milestones, code relationships, and technical specifications across sessions. It combines four memory subsystems: short-term memory for recent messages, long-term memory for permanent project information, episodic memory for chronological sequences, and semantic memory using vector embeddings for context-aware retrieval.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• mcp_cursor10x_initConversationmcp_cursor10x_initConversation({content: string, importance?: string, metadata?: object})

  Initializes a conversation by storing the user message, generating a banner, and retrieving context

  Try:Start a new conversation about implementing user authenticationTry:Begin discussing database design for the new projectTry:Initialize a conversation about optimizing API performance
• mcp_cursor10x_endConversationmcp_cursor10x_endConversation({content: string, milestone_title: string, milestone_description: string, importance?: string, metadata?: object})

  Ends a conversation by storing the assistant's final message and recording a milestone

  Try:Complete the conversation and record that we implemented the login systemTry:End the session and document the database changes madeTry:Finalize the conversation and note the completed API refactoring
• mcp_cursor10x_checkHealthmcp_cursor10x_checkHealth()

  Checks the health of the memory system and database connection

  Try:Check if the memory system is working properlyTry:Verify the health status of the memory databaseTry:Diagnose any issues with the context system
• mcp_cursor10x_getMemoryStatsmcp_cursor10x_getMemoryStats()

  Retrieves detailed statistics about the memory system

  Try:Show me the memory usage statisticsTry:Get information about how many messages are storedTry:Display the current memory system metrics
• mcp_cursor10x_getComprehensiveContextmcp_cursor10x_getComprehensiveContext()

  Retrieves unified context from all memory subsystems

  Try:Get all relevant context for the current conversationTry:Retrieve the complete project contextTry:Show me all relevant memories and active files
• mcp_cursor10x_storeUserMessagemcp_cursor10x_storeUserMessage({content: string, importance?: string, metadata?: object})

  Stores a user message in the short-term memory system

  Try:Save this user requirement for future referenceTry:Store this technical decision in memoryTry:Remember this important constraint about the implementation
• mcp_cursor10x_storeAssistantMessagemcp_cursor10x_storeAssistantMessage({content: string, importance?: string, metadata?: object})

  Stores an assistant message in the short-term memory system

  Try:Document the solution that was just providedTry:Save this recommendation for later useTry:Remember this implementation decision made by the AI
• mcp_cursor10x_trackActiveFilemcp_cursor10x_trackActiveFile({filename: string, action: string, metadata?: object})

  Tracks an active file being accessed or modified

  Try:Track that I'm now working on the authentication moduleTry:Record that I'm editing the database schemaTry:Note that I've opened the main application file

Comparable tools

Installation

# Install Turso CLI
curl -sSfL https://get.turso.tech/install.sh | bash

# Login to Turso
turso auth login

# Create a database
turso db create cursor10x-mcp

# Get database URL and token
turso db show cursor10x-mcp --url
turso db tokens create cursor10x-mcp

{
  "mcpServers": {
    "cursor10x-mcp": {
      "command": "npx",
      "args": ["cursor10x-mcp"],
      "enabled": true,
      "env": {
        "TURSO_DATABASE_URL": "your-turso-database-url",
        "TURSO_AUTH_TOKEN": "your-turso-auth-token"
      }
    }
  }
}

FAQ

What makes DevContext different from standard memory systems?

DevContext combines four distinct memory subsystems (short-term, long-term, episodic, and semantic) with vector embeddings for context-aware retrieval, providing more comprehensive and persistent context for AI assistants.

Can I use DevContext with AI assistants other than Claude?

While designed initially for Claude, DevContext is an MCP server and can be integrated with any AI tool that supports the MCP protocol.

Compare cursor10x-mcp with