tomschell/mcp-long-term-memory
If you are the rightful owner of mcp-long-term-memory and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
Memory MCP Server is a long-term memory storage system for LLMs using the Model Context Protocol (MCP) standard.
The Memory MCP Server is designed to enhance the capabilities of large language models (LLMs) by providing a robust long-term memory storage system. Utilizing the Model Context Protocol (MCP) standard, this server allows LLMs to retain and recall the context of work done over the entire history of a project, even across multiple sessions. By employing semantic search with embeddings, it can provide relevant context from past interactions and development decisions. This system is particularly useful for project-based memory organization, offering multiple memory types such as conversations, code, decisions, and references. It also supports rich metadata storage, a tagging system for memory organization, and relationship tracking between memories. The server is built on Node.js and uses SQLite for database management, with Ollama providing the embedding capabilities.
Features
- Project-based memory organization
- Semantic search using Ollama embeddings (nomic-embed-text model, 768 dimensions)
- Multiple memory types: Conversations, Code, Decisions, References
- Rich metadata storage including implementation status, key decisions, files created/modified, code changes, dependencies added
- Tagging system for memory organization and relationship tracking between memories
Usages
usage with local stdio
python mcp.run(transport='stdio') # Tools defined via @mcp.tool() decorator
usage with cursor
bash npm run dev # The server connects via stdio for Cursor compatibility
Tools
store-dev-memory
Create new development memories with content, type, tags, code changes, files created/modified, key decisions, and implementation status.
list-dev-memories
List existing memories with optional tag filtering.
get-dev-memory
Retrieve specific memory by ID.
search
Semantic search across memories using embeddings.
