MCP Memory Service

The MCP Memory Service is a semantic memory storage system based on ChromaDB and sentence transformers, providing long - term memory and semantic search functions for Claude Desktop.

Knowledge management and memory Artificial intelligence chatbots #Semantic Memory #Persistent Storage #Intelligent Search #Multi - Platform .Python

rating : 3.5 points

downloads : 269

update time : 2025-04-29

What is the MCP Memory Service?

The MCP Memory Service is an MCP server that provides semantic memory and persistent storage capabilities. It is suitable for long - term memory storage and context maintenance across conversation instances. It uses ChromaDB and sentence transformers to achieve efficient semantic search.

How to use the MCP Memory Service?

You can complete the installation and configuration in just a few steps. Enhance the conversation experience by storing, retrieving, and managing memories.

Applicable Scenarios

It is suitable for application scenarios that require long - term memory storage, such as personal assistants, customer service systems, and educational tools.

Main Features

Semantic SearchEfficient semantic memory retrieval is achieved through the sentence transformer model.

Natural Language Time RecallRetrieve memories using time expressed in natural language (e.g., 'last week', 'yesterday morning').

Tag - Based Memory RetrievalFind memories by specific tags.

Persistent StorageUse ChromaDB for persistent storage.

Automatic Database BackupRegularly back up the database to ensure data security.

Memory Optimization ToolClean up duplicates and optimize database performance.

Exact Match RetrievalRetrieve memories by exact content matching.

Debug ModeAnalyze similarity and view the retrieval process.

Database Health MonitoringCheck the database running status and obtain statistical information.

Duplicate CleanupAutomatically detect and delete duplicate entries.

Custom Embedding ModelSupport the selection of different embedding models.

Cross - Platform CompatibilitySupport multiple operating systems and hardware architectures.

Hardware - Aware OptimizationAdjust optimization strategies according to different environments.

Graceful FallbackProvide alternative solutions when resources are limited.

Advantages and Limitations

Advantages

Powerful semantic search capabilities.

Support multiple memory retrieval methods (time, tag, exact match, etc.).

Automatic backup and duplicate removal functions reduce manual intervention.

Strong cross - platform compatibility, suitable for different hardware architectures.

Hardware - aware optimization ensures optimal performance.

Limitations

More computing resources may be required for large databases.

Some advanced functions depend on network connectivity.

A certain technical background may be required for the initial deployment.

How to Use

Install UV

Make sure the UV tool is installed.

Clone and Install the Service

Clone the project and complete the installation.

Start the Service

Run the service to start using it.

Usage Examples

Store MemoryStore a new memory in the MCP Memory Service.

Retrieve MemoryRetrieve stored memories by keywords.

Frequently Asked Questions

How to check if the service is running normally?

How to clean up duplicate memories?

How to set up automatic backup?

Related Resources

GitHub Repository

Project source code and documentation.

Official Documentation

Detailed installation and usage guide.

Support Channel

Contact the developer for help.

🚀 MCP Memory Storage

A memory storage solution implemented with Cloudflare Workers

Overview

The MCP Memory Service is a memory storage solution built on Cloudflare Workers and the D1 database. It offers a set of tools for storing, retrieving, and managing memory content.

Core Components

Cloudflare Workers: Responsible for handling HTTP requests and responses.
D1 Database: Used for persistent storage of memory data, supporting SQLite-style queries.
Workers AI: Integrates AI models for content analysis and vectorization.
Server-Sent Events (SSE): Enables compatibility with the MCP protocol.

Features

Tool	Description
`store_memory`	Store new memory content, supporting optional tags.
`retrieve_memory`	Retrieve relevant memory content based on queries.
`recall_memory`	Retrieve memories using natural language time expressions.
`search_by_tag`	Search for memory content by tag.
`delete_memory`	Delete a specific memory based on its hash.
`delete_by_tag`	Delete all memories with a specified tag.
`cleanup_duplicates`	Identify and delete duplicate memory entries.
`get_embedding`	Obtain the original embedding vector of the content.
`check_embedding_model`	Check if the embedding model is loaded and working properly.
`debug_retrieve`	Retrieve memories with debugging information.
`exact_match_retrieve`	Retrieve memories using exact content matching.
`check_database_health`	Check the database health status and obtain statistical information.
`recall_by_timeframe`	Retrieve memory content based on a time range.
`delete_by_timeframe`	Delete memory content within a specified time period.
`delete_before_date`	Delete all memory content before a specified date.

Advantages

No Local Installation Required: No need to install any software or dependencies locally.
Cross-Platform Compatibility: Compatible with all devices that can access the Internet.
Auto-Scaling: Automatically adjusts resource allocation based on usage, eliminating the need for manual configuration.
Global Distribution: Achieves low-latency access through Cloudflare's global network.
No Maintenance Required: Automatically handles updates and maintenance tasks.

📦 Installation

1. Clone the code repository and enter the Cloudflare Workers directory

git clone https://github.com/doobidoo/mcp-memory-service.git
cd mcp-memory-service/cloudflare_worker

2. Install the Wrangler CLI tool

Wrangler is a command-line tool provided by Cloudflare for managing and deploying Workers.

npm install -g wrangler

3. Log in to your Cloudflare account

Use the installed Wrangler to log in to your Cloudflare account.

wrangler login

4. Create a D1 database

Create a new D1 database instance on the Cloudflare platform.

wrangler d1 create mcp_memory_service

5. Update the wrangler.toml configuration file

Update the wrangler.toml file according to the created database ID.

Featured MCP Services

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.

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.

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.

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.

554

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.

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.

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

745

4.8 points

Zhiqi Future, Your AI Solution Think Tank

English 简体中文繁體中文にほんご