MCP Memory Service
Provides semantic memory and persistent storage for Claude, leveraging ChromaDB and sentence transformers for enhanced search and retrieval capabilities.
What is MCP Memory Service?
MCP Memory Service is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides semantic memory and persistent storage for claude, leveraging chromadb and sentence transformers for enhanced search and retrieval capabilities.
Provides semantic memory and persistent storage for Claude, leveraging ChromaDB and sentence transformers for enhanced search and retrieval capabilities.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Provides semantic memory and persistent storage for Claude,
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-memory-serviceConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MCP Memory Service
MCP Memory Service provides semantic memory and persistent storage for Claude using ChromaDB and sentence transformers for enhanced search and retrieval. When connected, this server enables you to build long-term memory for agents and conversations, automatically storing and retrieving contextual information across sessions—perfect for personalized AI assistants with evolving knowledge.
Prerequisites
- Python 3.8+ installed
- An MCP client such as Claude Desktop, Cursor, or VS Code
- ChromaDB and sentence-transformers libraries available
Clone the MCP Memory Service repository
Clone the repository to access the semantic memory implementation.
git clone https://github.com/doobidoo/mcp-memory-service.git
cd mcp-memory-serviceInstall Python dependencies
Install ChromaDB, sentence-transformers, and other required packages.
pip install -r requirements.txtInitialize the ChromaDB database
Create the initial database for semantic memory storage.
python init_memory.pyAdd to your MCP client configuration
Register the Memory Service in your Claude Desktop config.
{
"mcpServers": {
"memory-service": {
"command": "python",
"args": ["-m", "mcp_memory_service"]
}
}
}Verify memory storage is working
Restart your client and ask Claude to store and retrieve a test memory to confirm functionality.
MCP Memory Service Examples
Client Configuration Example
Configuration for MCP Memory Service in your MCP client:
{
"mcpServers": {
"memory-service": {
"command": "python",
"args": ["-m", "mcp_memory_service"]
}
}
}Prompts to try
Example prompts for semantic memory operations:
1. "Remember that I prefer TypeScript over Python for my projects"
2. "What preferences or facts have I stored in memory?"
3. "Search my memories for information about my favorite coding patterns"
4. "Store this important context: my project uses React 18 and Next.js 13"Troubleshooting MCP Memory Service
ChromaDB initialization fails
Ensure ChromaDB is correctly installed: 'pip install chromadb'. Verify the database directory exists and has write permissions.
Memory retrieval returns irrelevant results
This can occur if sentence embeddings don't match expectations. Try clearing the database and retraining on your specific domain. Refer to the repository README for embedding model configuration.
Frequently Asked Questions about MCP Memory Service
What is MCP Memory Service?
MCP Memory Service is a Model Context Protocol (MCP) server that provides semantic memory and persistent storage for claude, leveraging chromadb and sentence transformers for enhanced search and retrieval capabilities. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MCP Memory Service?
Follow the installation instructions on the MCP Memory Service GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MCP Memory Service?
MCP Memory Service works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MCP Memory Service free to use?
Yes, MCP Memory Service is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
MCP Memory Service Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to MCP Memory Service? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
Claude Scholar
★ 4.0kSemi-automated research assistant for academic research and software development. Supports Claude Code, OpenCode, and Codex CLI across ideation, coding, experiments, writing, and publication.
Continuous Claude V3
★ 3.8kContext management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.
Obsidian MCP
★ 3.8kMCP server that interacts with Obsidian via the Obsidian rest API community plugin
Zotero
★ 3.3kAn AI-powered research assistant that integrates with Zotero to read academic papers, create intelligent annotations, and generate structured notes. It enables users to highlight findings, explain formulas, and write comprehensive summaries directly
Browse More Knowledge & Memory MCP Servers
Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MCP Memory Service in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MCP Memory Service?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.