Cursor10x Memory
The Cursor10x Memory System creates a persistent memory layer for AI assistants (specifically Claude), enabling them to retain and recall short-term, long-term and episodic memory on autonomously.
What is Cursor10x Memory?
Cursor10x Memory is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to cursor10x memory system creates a persistent memory layer for ai assistants (specifically claude), enabling them to retain and recall short-term, long-term and episodic memory on autonomously.
The Cursor10x Memory System creates a persistent memory layer for AI assistants (specifically Claude), enabling them to retain and recall short-term, long-term and episodic memory on autonomously.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- The Cursor10x Memory System creates a persistent memory laye
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx cursor10x-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Cursor10x Memory
Cursor10x MCP (now called DevContext) provides a persistent, structured memory layer for AI coding assistants by storing context in a Turso LibSQL cloud database. It implements four complementary memory types — short-term, long-term, episodic, and semantic vector memory — so assistants can recall recent files, architectural decisions, past actions, and code snippets across sessions, eliminating the need to re-explain project context at the start of every conversation.
Prerequisites
- Node.js 18+ (for npx) or the ability to run the server directly
- A Turso account (turso.tech) — free tier is sufficient for personal use
- Turso CLI installed and authenticated to create a database and generate an auth token
- An MCP-compatible client such as Cursor or Claude Desktop
Install the Turso CLI and authenticate
Turso is the LibSQL cloud database that stores all memory. Install its CLI and log in to your account.
curl -sSfL https://get.turso.tech/install.sh | bash
turso auth loginCreate a Turso database for cursor10x
Create a dedicated database and retrieve its connection URL and an auth token. Keep both values — they go into the MCP config.
turso db create cursor10x-mcp
turso db show cursor10x-mcp --url
turso db tokens create cursor10x-mcpAdd cursor10x-mcp to your MCP client configuration
Open your client's MCP config file (.cursor/mcp.json for Cursor, claude_desktop_config.json for Claude Desktop) and add the server entry with the Turso credentials.
{
"mcpServers": {
"cursor10x-mcp": {
"command": "npx",
"args": ["-y", "cursor10x-mcp"],
"env": {
"TURSO_DATABASE_URL": "libsql://cursor10x-mcp-<your-org>.turso.io",
"TURSO_AUTH_TOKEN": "your-turso-auth-token"
}
}
}
}Initialize a conversation session
At the start of each work session, call initConversation to generate a context banner that summarizes recent messages, active files, milestones, and past episodes. This seeds the assistant with everything it needs to continue where you left off.
Store key decisions and milestones during work
As you work, ask the assistant to record important context — architectural decisions, completed milestones, and code snippets — using the long-term memory tools. This builds the knowledge base that future sessions draw from.
End sessions with endConversation
Before closing your client, ask the assistant to call endConversation. This finalizes storage of the session's messages, milestones, and episodes, ensuring the next session picks up accurate context.
Cursor10x Memory Examples
Client configuration
Complete MCP config for cursor10x-mcp using Turso database credentials. Works in both Cursor (.cursor/mcp.json) and Claude Desktop (claude_desktop_config.json).
{
"mcpServers": {
"cursor10x-mcp": {
"command": "npx",
"args": ["-y", "cursor10x-mcp"],
"env": {
"TURSO_DATABASE_URL": "libsql://cursor10x-mcp-yourorg.turso.io",
"TURSO_AUTH_TOKEN": "eyJhbGci..."
}
}
}
}Prompts to try
Prompts that leverage the four memory systems for persistent context across sessions.
- "Initialize this conversation and show me what you remember from our last session"
- "Store a milestone: completed OAuth integration with GitHub provider"
- "Record an architectural decision: we chose PostgreSQL over MongoDB for relational data needs"
- "What files have I been editing most recently?"
- "Search your semantic memory for anything related to our authentication system"Troubleshooting Cursor10x Memory
Connection error: TURSO_DATABASE_URL or TURSO_AUTH_TOKEN invalid
Re-run 'turso db show cursor10x-mcp --url' to get the exact URL and 'turso db tokens create cursor10x-mcp' for a fresh token. The URL format must be libsql:// not https://. Tokens expire — create a new one if you see authentication failures.
Memory tools return empty results even after storing data
Run mcp_cursor10x_checkHealth to verify database connectivity. If the database tables are missing, the first call to initConversation should create them automatically. If not, check that your Turso auth token has write permissions on the database.
Vector similarity search returns no results
Semantic memory (mcp_cursor10x_manageVector) requires that embeddings have been stored first via the store operation. Ensure you are running a version that supports F32_BLOB vector storage, and verify the similarity threshold is not set too high (default works for most cases).
Frequently Asked Questions about Cursor10x Memory
What is Cursor10x Memory?
Cursor10x Memory is a Model Context Protocol (MCP) server that cursor10x memory system creates a persistent memory layer for ai assistants (specifically claude), enabling them to retain and recall short-term, long-term and episodic memory on autonomously. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Cursor10x Memory?
Follow the installation instructions on the Cursor10x Memory GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Cursor10x Memory?
Cursor10x Memory works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Cursor10x Memory free to use?
Yes, Cursor10x Memory is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Cursor10x Memory Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Cursor10x Memory? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Cursor10x Memory in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Cursor10x Memory?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.