Cursor10x MCP

The Cursor10x MCP is a persistent multi-dimensional memory system for Cursor that enhances AI assistants with conversation context, project history, and code relationships across sessions.

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "aiurda-cursor10x-mcp": {
      "command": "npx",
      "args": [
        "cursor10x-mcp"
      ],
      "env": {
        "TURSO_AUTH_TOKEN": "YOUR_TURSO_AUTH_TOKEN",
        "TURSO_DATABASE_URL": "YOUR_TURSO_DATABASE_URL"
      }
    }
  }
}

DevContext MCP Server provides a dedicated, autonomous memory context system that helps AI assistants stay aware of your project across sessions. It organizes memory into short-term, long-term, episodic, and semantic layers, enabling fast, relevance-based retrieval and seamless code-aware interactions for development workflows.

How to use

You operate DevContext MCP Server through an MCP client that talks to the local stdio server. Start the server locally, then run commands from your project to initialize conversations, store and retrieve memory, and manage context for ongoing development tasks.

Available tools

mcp_cursor10x_initConversation

Initializes a conversation by storing the user message, generating a banner, and retrieving context in one operation, reducing setup steps at the start of conversations.

mcp_cursor10x_endConversation

Ends a conversation by storing the assistant's final message, recording a milestone, and logging an episode in episodic memory.

mcp_cursor10x_checkHealth

Checks the health of the memory system and its database connection.

mcp_cursor10x_getMemoryStats

Retrieves detailed statistics about the memory system.

mcp_cursor10x_getComprehensiveContext

Retrieves a unified context from all memory subsystems to inform the current interaction.

mcp_cursor10x_storeUserMessage

Stores a user message in short-term memory with optional importance and metadata.

mcp_cursor10x_storeAssistantMessage

Stores an assistant message in short-term memory with optional importance and metadata.

mcp_cursor10x_trackActiveFile

Tracks an active file being accessed or modified by the user.

mcp_cursor10x_getRecentMessages

Retrieves recent messages from short-term memory with optional filters.

mcp_cursor10x_getActiveFiles

Retrieves currently active files from short-term memory.

mcp_cursor10x_storeMilestone

Stores a project milestone in long-term memory.

mcp_cursor10x_storeDecision

Stores a project decision in long-term memory.

mcp_cursor10x_storeRequirement

Stores a project requirement in long-term memory.

mcp_cursor10x_recordEpisode

Records an episodic memory item describing an action within the project.

mcp_cursor10x_getRecentEpisodes

Retrieves recent episodes from episodic memory.

mcp_cursor10x_manageVector

Unified tool for storing and querying vector embeddings for semantic search across memory.

Built by

VeilStrat

AI signals for GTM teams