AI-MCP-SQL: SQL Persistent Memory Server with VS Code CRUD Support

Ai MCP Sql

A SQL persistent memory server project based on the MCP protocol, supporting CRUD operations through the Gemini Code Assist extension in VS Code, including storing, retrieving, updating, and deleting memory data.

Knowledge management and memory Developer tools #MCP Server #SQL Memory #CRUD Operations #VS Code Extension .Python

rating : 2 points

downloads : 7.9K

update time : 2026-03-12

Open Site

What is the Persistent Memory Assistant?

The Persistent Memory Assistant is an intelligent memory management system that allows you to store and retrieve important information when interacting with Gemini Code Assist (Google's AI programming assistant). Just like having an external memory bank for your brain, you can save project details, contact information, configuration settings, etc. at any time and quickly retrieve them when needed.

How to use the Persistent Memory Assistant?

You only need to install the Gemini Code Assist extension in VS Code and perform simple configuration. Then you can manage your memory through natural language instructions (such as 'Remember that my project leader is Alex' or 'Who is my project leader?'). All operations are completed in the chat interface without writing code.

Applicable Scenarios

It is very suitable for developers, project managers, or anyone who needs to frequently handle information from multiple projects. For example: remember the configuration parameters of different projects, contact information of team members, temporary code snippets, meeting points, or to - do items.

Main Features

Store Memory (Create)

Save any text information (such as contacts, configurations, ideas) in the form of 'key - value' pairs to the local database through simple natural language instructions.

Retrieve Memory (Read)

Quickly find and obtain previously stored information through keywords or descriptions. The system will understand your intention and find the most relevant memory.

Browse All Memories

View all saved memory entries with one click, making it convenient for you to review and manage the entire memory library.

Update Memory (Update)

When the information changes (such as a contact change), you can directly update the existing memory content to keep the information up - to - date.

Delete Memory (Delete)

Clean up old information that is no longer needed to keep the memory library tidy and relevant.

Seamless VS Code Integration

Runs as an MCP server and is deeply integrated into the Gemini Code Assist chat interface in VS Code, eliminating the need to switch applications.

Advantages

Simple operation: Manage memory completely through natural language conversations without memorizing complex commands.

Persistent storage: Information is saved in the local database and will not be lost even after closing VS Code.

Privacy and security: All data is stored on your own computer and is not uploaded to the cloud.

Improve efficiency: Quickly access key project information, reducing the burden of repeated searching and memorization.

Flexible management: Supports complete Create, Read, Update, and Delete (CRUD) operations to adapt to dynamic information changes.

Limitations

Dependent on a specific environment: Requires VS Code and the Gemini Code Assist extension.

Initial configuration steps: One - time path configuration is required for the first use.

Text - based: Currently mainly stores text information, with limited support for complex structured data.

Local storage: Data only exists on the configured computer, and no cross - device synchronization function is provided.

How to Use

Install Required Extensions

Search for and install the 'Gemini Code Assist' extension in the VS Code extension marketplace. After installation, make sure to switch its mode to 'Agent mode' in the extension settings.

Create a Configuration File

In your user directory (such as C:/Users/Your Username/.gemini/), find or create the `settings.json` file. Copy the provided configuration code block into this file. Note: You need to modify the values of `command` and `args` according to the actual paths of Python and project files on your computer.

Restart and Initialize

After modifying the configuration, make sure to completely restart VS Code for the settings to take effect. After reopening, enter the `/init` command in the Gemini Code Assist chat box to initialize the AI agent.

View Available Tools

After successful initialization, enter the `/mcp` command. The AI assistant will list all available tools, and you should be able to see the service named'my - persistent - memory' and the tools it provides (such as store_memory, retrieve_memory, etc.).

Start Using

Now, you can directly issue instructions to the Gemini assistant in natural language to use the memory function, for example: 'Remember that my project manager is Sarah'.