mcp-memory-graph

RetroRobAI/mcp-memory-graph
★ 0 stars Python 🤖 AI/LLM Updated today
Context-aware memory MCP server with authority weighting, conflict detection, and typed relationship edges — so your AI agent always retrieves the most trustworthy answer when memories conflict.
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-memory-graph": {
      "command": "uvx",
      "args": [
        "mcp-memory-graph"
      ]
    }
  }
}

Or install with pip: pip install mcp-memory-graph

README Excerpt

<!-- mcp-name: io.github.RetroRobAI/mcp-memory-graph --> A context-aware memory MCP server for Claude Code and any MCP-compatible AI agent. Goes beyond basic vector search by adding **authority weighting**, **conflict detection**, and **typed relationship edges** between memories — so your agent always retrieves the right answer when sources disagree.

Tools (14)

MEMORY_GRAPH_CONFLICT_THRESHOLDMEMORY_GRAPH_DB_PATHMEMORY_GRAPH_DEFAULT_RESULTSMEMORY_GRAPH_DIMMEMORY_GRAPH_MODELadd_memory_edgecheck_conflictsdelete_memoryget_related_memorieslist_memoriesmcpServersretrieve_memoriesstore_memoryupdate_memory

Topics

ai-agentanthropicclaudeknowledge-graphllmmcpmemorypythonsemantic-search