MyBrAIn
myBrAIn is an MCP (Model Context Protocol) server designed to provide persistent and contextual memory to language models (like Google Antigravity). It acts as a 'second brain' for your development environment, allowing the AI to remember project rul
What is MyBrAIn?
MyBrAIn is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mybrain is an mcp (model context protocol) server designed to provide persistent and contextual memory to language models (like google antigravity). it acts as a 'second brain' for your development en...
myBrAIn is an MCP (Model Context Protocol) server designed to provide persistent and contextual memory to language models (like Google Antigravity). It acts as a 'second brain' for your development environment, allowing the AI to remember project rul
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- myBrAIn is an MCP (Model Context Protocol) server designed t
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mybrainConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MyBrAIn
myBrAIn is an MCP server that provides AI coding assistants with a persistent, contextual memory layer — acting as a second brain that survives across sessions and projects. It allows the AI to store architectural rules, recall relevant project context, and critique code against previously saved guidelines so that it never loses track of decisions made earlier in the development lifecycle. Teams use it to enforce consistency, remember project-specific conventions, and reduce the need to re-explain context on every new conversation.
Prerequisites
- Python 3.10+ (for local setup) or Docker and Docker Compose (for recommended containerized setup)
- Git to clone the repository
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
- Streamlit (installed automatically via requirements.txt) for the optional admin dashboard
Clone the repository
Clone myBrAIn from GitHub to your local machine.
git clone https://github.com/lilium360/myBrAIn.git
cd myBrAInConfigure the environment
Copy the example environment file to create your own .env. Edit it to set your data directory and any other options defined in core/config.py.
cp .env.example .envStart with Docker (recommended)
The Docker Compose setup launches both the MCP server and the Streamlit admin dashboard automatically.
docker compose up -dOr install locally with Python
If you prefer not to use Docker, create a virtual environment and install dependencies directly.
python3 -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
# Start the admin dashboard separately:
streamlit run admin.pyConfigure your MCP client
Add myBrAIn to your MCP client config. For Docker, point to the running container; for local Python, use the absolute path to the venv Python binary.
{
"mcpServers": {
"mybrain": {
"command": "python",
"args": ["/absolute/path/to/myBrAIn/main.py"],
"env": {
"MYBRAIN_DATA_DIR": "/absolute/path/to/myBrAIn/data"
}
}
}
}Initialize a workbase and store context
Once connected, link your project directory to the memory system and start storing insights about your architecture and rules.
MyBrAIn Examples
Client configuration
Claude Desktop configuration for myBrAIn running locally with Python.
{
"mcpServers": {
"mybrain": {
"command": "/absolute/path/to/myBrAIn/venv/bin/python",
"args": ["/absolute/path/to/myBrAIn/main.py"],
"env": {
"MYBRAIN_DATA_DIR": "/absolute/path/to/myBrAIn/data"
}
}
}
}Prompts to try
Example prompts that exercise myBrAIn's memory and critique tools.
- "Initialize a workbase for my project at /home/user/myapp"
- "Store an insight: all API endpoints must return JSON and use snake_case field names"
- "Recall context about our authentication strategy"
- "Critique this new AuthController code against the stored architectural guidelines"
- "Audit the codebase at /home/user/myapp for architectural drift from our stored rules"Troubleshooting MyBrAIn
The MCP server fails to start because Python cannot find the required modules
Make sure you activated the virtual environment before running and that 'pip install -r requirements.txt' completed without errors. Use the absolute path to the venv Python binary in your MCP client config.
Stored insights are not persisting between sessions
Confirm that MYBRAIN_DATA_DIR points to a writable directory that is not cleaned between runs. When using Docker, ensure the data volume is correctly mounted in docker-compose.yml.
Frequently Asked Questions about MyBrAIn
What is MyBrAIn?
MyBrAIn is a Model Context Protocol (MCP) server that mybrain is an mcp (model context protocol) server designed to provide persistent and contextual memory to language models (like google antigravity). it acts as a 'second brain' for your development environment, allowing the ai to remember project rul It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MyBrAIn?
Follow the installation instructions on the MyBrAIn GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MyBrAIn?
MyBrAIn works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MyBrAIn free to use?
Yes, MyBrAIn is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
MyBrAIn Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MyBrAIn? 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 MyBrAIn 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 MyBrAIn?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.