cursor10x
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.
claude mcp add --transport stdio aiurda-cursor10x-mcp npx cursor10x-mcp \ --env TURSO_AUTH_TOKEN="your-turso-auth-token" \ --env TURSO_DATABASE_URL="your-turso-database-url"
How to use
DevContext (formerly Cursor10x) is an MCP server that provides a persistent, project-centric memory and context system for your AI assistants. It combines short-term, long-term, episodic, and semantic memory to maintain continuity across sessions, store important milestones, track code structure, and enable fast semantic search over your project data. The server exposes tools that register with the MCP protocol, allowing you to initialize conversations, fetch banners, and retrieve context automatically as you work. Using Diff-based and vector-embedding storage, it can recall recent messages, active files, and code components, while also indexing code structures for quick cross-referencing. To start using it, run the MCP server via the configured command, connect your agent, and invoke system tools such as mcp_cursor10x_initConversation to begin a session with a generated banner and comprehensive context ready for the assistant.
How to install
Prerequisites:\n- Node.js 18 or higher\n- npm or yarn\n- Turso database account (free tier is fine)\n\nSetup steps:\n1) Install and login to Turso (if you don’t have a Turso project yet):\nbash\ncurl -sSfL https://get.turso.tech/install.sh | bash\n\nturso auth login\n\n2) Create your Turso database for the MCP server memory store:\nbash\nturso db create cursor10x-mcp\n\n3) Retrieve connection details (URL and token) for your MCP configuration:\nbash\nturso db show cursor10x-mcp --url\nturso db tokens create cursor10x-mcp\n\n4) Configure the MCP server to use Turso by creating or updating your mcp.json (see example below). You can also place this in a project subdirectory like .cursor/mcp.json.\njson\n{\n "mcpServers": {\n "cursor10x-mcp": {\n "command": "npx",\n "args": ["cursor10x-mcp"],\n "enabled": true,\n "env": {\n "TURSO_DATABASE_URL": "your-turso-database-url",\n "TURSO_AUTH_TOKEN": "your-turso-auth-token"\n }\n }\n }\n}\n\n5) Start the MCP server: simply run the configured command (npx cursor10x-mcp) or start via your process manager. This will register the server under the configured mcpServers entry.\n6) Connect your MCP-enabled agent to the running server and begin using tools like mcp_cursor10x_initConversation to initialize sessions.\n
Additional notes
Tips and common issues:\n- Ensure TURSO_DATABASE_URL and TURSO_AUTH_TOKEN are kept secure; do not commit them to source control.\n- The server uses Turso for persistent storage; verify you have network access to Turso services and the URL/token are valid.\n- If you update environment variables, restart the MCP server to apply changes.\n- The mcp_cursor10x_initConversation tool provides a unified entry point to generate a banner and fetch context in one call; use it at the start of every conversation to maximize context continuity.\n- You can access the database URL via turso db show cursor10x-mcp --url and manage credentials with turso db tokens create cursor10x-mcp.\n- For local testing, you can mock TURSO credentials but remember to replace them in production.\n
Related MCP Servers
wanaku
Wanaku MCP Router
adb
An MCP (Model Context Protocol) server for interacting with Android devices through ADB in TypeScript.
fast -telegram
Telegram MCP Server and HTTP-MTProto bridge | Multi-user auth, intelligent search, file sending, web setup | Docker & PyPI ready
memory
A MCP (Model Context Protocol) server providing long-term memory for LLMs
mongo
MCP server that provide tools to LLMs such as claude in cursor to interact with MongoDB
mcp -nodejs-api-docs
MCP Server for Node.js API documentation