The Memory Bank MCP Server integrates Cline's Memory Bank pattern to create structured documentation systems for AI assistants. This server helps you organize project knowledge in a standardized way, making context preservation more effective when working with AI coding assistants.
Add this configuration to your mcp.json file:
{
"mcpServers": {
"mcp-memory-bank": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/ipospelov/mcp-memory-bank",
"mcp_memory_bank"
]
}
}
}
Configure your mcp.json file with:
{
"mcpServers": {
"memory-bank": {
"command": "npx",
"args": [
"-y",
"@smithery/cli@latest",
"run",
"@ipospelov/mcp-memory-bank",
"--key",
"your_smithery_key"
]
}
}
}
Add this to your mcp.json config file:
{
"mcpServers": {
"memory-bank": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"19283744/mcp-memory-bank:latest"
]
}
}
}
Clone the repository and run:
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
Then configure your mcp.json:
{
"mcpServers": {
"memory-bank": {
"command": "python",
"args": ["src/mcp_memory_bank/main.py"]
}
}
}
After installation, you can interact with your AI assistant by asking it to work with Memory Bank. For example:
Create memory bank for To Do list application with your tools
Providing more detailed context about your project will give you better results.
Use the get_memory_bank_structure
tool to retrieve a detailed description of the Memory Bank file structure.
The generate_memory_bank_template
tool creates templates for specific Memory Bank files:
{
"file_name": "projectbrief.md"
}
Analyze your project and get Memory Bank content suggestions with the analyze_project_summary
tool:
{
"project_summary": "Building a React web app for inventory management with barcode scanning"
}
The Memory Bank consists of these key markdown files:
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cursor-rules-mcp": {
"command": "npx",
"args": [
"-y",
"cursor-rules-mcp"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.