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.
rating : 2 points
downloads : 6.9K
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'.
Usage Examples
Example 1: Store Key Project Information
You are starting a new project and need to remember the project leader and the main technology stack.
Example 2: Manage Temporary Configurations
You used a temporary API endpoint during debugging and hope to remember it quickly next time.
Example 3: Update Contact Information
The project contact has changed, and you need to update the saved information.
Example 4: Clean Up Expired Information
An old project has ended, and the relevant configuration information is no longer needed.
Frequently Asked Questions
What should I do if the new tool does not appear after modifying the configuration file?
Where is my memory data stored? Is it safe?
How many memories can I store?
Can I store pictures or files in addition to text?
Why can't the AI sometimes find the memory I just saved?
Related Resources
Gemini Code Assist Extension Homepage
View the official documentation and installation guide in the VS Code extension marketplace.
Model Context Protocol (MCP) Official Documentation
Understand the detailed specifications, design concepts, and more server examples of the MCP protocol.
This Project's Code Repository (Example)
View the source code of this persistent memory server to understand its implementation principle.

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.4K
4.5 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.3K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.4K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.8K
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.4K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.2K
5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
21.0K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
98.2K
4.7 points



