MCP Memory Service (rust Implementation)
This is an MCP Memory Service implemented in Rust, providing memory storage and retrieval functions, supporting multiple storage backends and embedding models, and communicating with clients via the JSON-RPC protocol.
rating : 2 points
downloads : 8
What is the MCP Memory Service?
The MCP Memory Service is a memory storage and retrieval tool based on the Model Context Protocol (MCP), allowing users to store, retrieve, search for, and delete memory records with content, tags, and metadata. It communicates via standard input/output (stdio), facilitating integration with other MCP clients.How to use the MCP Memory Service?
Users can interact with the service by sending JSON-RPC requests. First, start the service, and then send requests via the command line or client tools to perform functions such as storage and retrieval.Applicable Scenarios
Suitable for application scenarios requiring efficient memory management, such as knowledge base construction, dialogue system development, and intelligent assistant development.Main Features
Store MemorySave new memories and their related content, tags, and metadata to the system.
Retrieve MemoryRetrieve the most similar memories based on the query statement.
Search by TagFind relevant memories by specifying tags.
Delete MemoryDelete specific memories based on the memory hash value.
Support for Multiple Storage BackendsSupports in-memory storage (for development and testing) and ChromaDB storage (for production environments).
Support for Multiple Embedding ModelsSupports the Dummy embedding generator and ONNX embedding models.
Advantages and Limitations
Advantages
Easy to integrate into other MCP clients.
Supports multiple storage and embedding models to meet different needs.
Efficient memory management and retrieval capabilities.
Open source and free to use.
Limitations
Requires a certain technical background to fully utilize its functions.
ONNX models may require additional hardware acceleration (e.g., GPU).
How to Use
Install Dependencies
Ensure that Rust, Cargo, and Node.js are installed.
Build the Project
Build the MCP Memory Service using Cargo.
Run the Service
Start the service and set environment variables.
Send Requests
Send requests such as storage and retrieval via JSON-RPC.
Usage Examples
Store MemoryAdd a new memory to the system.
Retrieve MemoryFind similar memories based on the query statement.
Frequently Asked Questions
How to choose the appropriate storage backend?
How to configure the ONNX embedding model?
Related Resources
Official GitHub Repository
The official code repository for the MCP Rust SDK.
MCP Documentation
The complete documentation for the MCP protocol.
ONNX Runtime
The official website of ONNX Runtime.
Featured MCP Services

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
95
4.3 points

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
148
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
1.7K
5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
836
4.3 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#
572
5 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
6.7K
4.5 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
286
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
760
4.8 points