- Vector Memory Mcp Server
Vector Memory Mcp Server
What is Vector Memory MCP Server?
Vector Memory MCP Server is a secure, vector-based memory server designed for Claude Desktop, utilizing sqlite-vec and sentence-transformers to provide persistent semantic memory capabilities. It enhances AI coding assistants by remembering and retrieving relevant coding experiences, solutions, and knowledge.
How to use Vector Memory MCP Server?
To use the Vector Memory MCP Server, install it via the uv package manager and configure it with Claude Desktop. You can run it directly using the command: uvx vector-memory-mcp --working-dir /path/to/your/project.
Key features of Vector Memory MCP Server?
- Semantic Search: Vector-based similarity search using 384-dimensional embeddings.
- Persistent Storage: SQLite database with vector indexing via sqlite-vec.
- Smart Organization: Categories and tags for better memory organization.
- Security First: Input validation, path sanitization, and resource limits.
- High Performance: Fast embedding generation with sentence-transformers.
- Auto-Cleanup: Intelligent memory management and cleanup tools.
- Rich Statistics: Comprehensive memory database analytics.
- Automatic Deduplication: Prevents storing duplicate memories using SHA-256 content hashing.
Use cases of Vector Memory MCP Server?
- Storing coding experiences and solutions for easy retrieval.
- Enhancing team workflows by sharing coding conventions and deployment procedures.
- Supporting individual developers in learning and growth by storing insights and debugging discoveries.
FAQ from Vector Memory MCP Server?
-
Can I use it for all programming languages?
Yes, it is designed to store and retrieve memories related to any programming language. -
Is it secure?
Yes, it includes various security features such as input validation and path sanitization. -
How does semantic search work?
It uses sentence-transformers to convert memories into vectors that capture semantic meaning, allowing for effective similarity searches.
Server Config
{
"mcpServers": {
"vector-memory": {
"command": "uvx",
"args": [
"vector-memory-mcp",
"--working-dir",
"/absolute/path/to/your/project"
]
}
}
}