Simple Memory Extension MCP server

This MCP server extends the context window/memory of agents, helping them store and recall important information during coding sessions. It's especially useful when building larger features or maintaining context across conversations.

Installation

To install and run the MCP server, follow these simple steps:

npm install
npm start

This will install all required dependencies and start the server.

Configuration

The server can be configured using environment variables in a .env file:

# Path to SQLite database file
DB_PATH=./data/context.db

PORT=3000

# Use HTTP SSE or Stdio
USE_HTTP_SSE=true

# Logging Configuration: debug, info, warn, error
LOG_LEVEL=info

Available Tools

The MCP server provides several tools for managing context and memory:

Context Item Management

• Store Context Item: Save information with a specific key in a namespace
• Retrieve Context Item by Key: Get stored information using its key
• Delete Context Item: Remove specific key-value pairs from storage

Namespace Management

• Create Namespace: Set up a new storage area
• Delete Namespace: Remove an entire namespace and all its contents
• List Namespaces: View all available namespaces
• List Context Item Keys: See all keys stored in a specific namespace

Semantic Search

• Retrieve Context Items by Semantic Search: Find stored information based on meaning rather than exact key matches

Semantic Search Capabilities

The server includes powerful semantic search functionality that:

1. Converts queries to vectors using the E5 model
2. Automatically splits text into chunks for better matching
3. Calculates similarity between your query and stored information
4. Returns the most relevant matches sorted by similarity

The semantic search feature uses the multilingual E5 model from Hugging Face and should be automatically set up when you start the server.

Usage Examples

Basic Memory Storage and Retrieval

To store information:

store_context_item(namespace, key, value)

To retrieve information:

retrieve_context_item_by_key(namespace, key)

Using Semantic Search

When you need to find information but don't remember the exact key:

retrieve_context_items_by_semantic_search(namespace, query, max_results)

This will return the most semantically similar items to your query, helping you locate relevant information even without knowing the exact keys.

How to add this MCP server to Cursor

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.

Adding an MCP server to Cursor globally

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"
            ]
        }
    }
}

Adding an MCP server to a project

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.

How to use the MCP server

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.