Name: Memory MCP Server
Availability: InStock
Author: pomazanbohdan

What it does

This server provides a sophisticated long-term memory system for AI agents, enabling them to maintain state across sessions. It combines vector search for semantic retrieval, a knowledge graph for entity relationships, and deep codebase indexing to turn stateless chatbots into stateful workers.

Tools

recall: Hybrid search using Vector, Keyword, and Graph fusion (RRF).
store_memory: Save new memories with optional metadata.
knowledge_graph: Create entities, relations, and detect communities in the knowledge graph.
index_project: Index local codebase directories for deep code search.
recall_code: Retrieve code using hybrid vector and BM25 search.
symbol_graph: Navigate codebase symbols via callers, callees, and related symbols.
search_memory: Targeted search using either vector or BM25 modes.

Installation

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "memory": {
      "command": "docker",
      "args": [
        "run",
        "--init",
        "-i",
        "--rm",
        "--memory=3g",
        "-v", "mcp-data:/data",
        "-v", "/absolute/path/to/your/project:/project:ro",
        "ghcr.io/pomazanbohdan/memory-mcp-1file:latest"
      ]
    }
  }
}