A universal MCP server providing persistent, structured memory through a knowledge graph with graph storage, semantic vector search, and multi-hop traversal for AI agents and IDEs.
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find.
Install from
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
process.env. You'll be asked to provide them before it can run.GRAPHMEM_DB_PATH— env export GRAPHMEM_DB_PATH=/tmp/test.db Stores at that pathGRAPHMEM_TRANSPORT— transport stdio MCP transport protocolGRAPHMEM_EMBEDDING_MODEL— embedding-model all-MiniLM-L6-v2 HuggingFace model IDGRAPHMEM_USE_ONNX— use-onnx / --no-onnx false Use ONNX runtime if availableGRAPHMEM_EMBEDDING_DEVICE— embedding-device cpu Inference device (cpu or cuda)GRAPHMEM_CACHE_SIZE— cache-size 10000 Embedding cache max entriesGRAPHMEM_SEARCH_LIMIT— search-limit 10 Default search result limitGRAPHMEM_MAX_HOPS— max-hops 4 Default max traversal depthGRAPHMEM_LOG_LEVEL— log-level WARNING Logging verbosity[](https://m8ven.ai/mcp/sathvik-1007-graphmem-mcp-1k4ulp)