74
/ 100
29 days ago
glama

mcp-memory-graph

Local-first memory for Claude Code and any MCP client: hybrid vector + keyword search and a bi-temporal knowledge graph in one SQLite file. Local embeddings, no API key, $0/token.

Is this your MCP?

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.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
🔐
You'll be asked for 1 credential: MCP_AUTH_TOKEN
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// required environment variables
This server reads these from process.env. You'll be asked to provide them before it can run.
configBENCH_CORPUS_SCALE
configBENCH_DB
configCLAUDE_BINFor the Stop hook only: the claude binary on $PATH (or $), authenticated without prompting. Optional; disable with review_on_stop: false.
configCYCLES
configMCP_AGENT_IDAttribution: set (or pass agent_id per store) and memory_attribution reports how many valid memories each agent wrote.
configMCP_ALLOWED_ORIGINS
configMCP_API_NAMESPACE
configMCP_AUTH_OPTIONAL
🔐 secretMCP_AUTH_TOKEN$(openssl rand -hex 32) MCP_BIND=0.0.0.0 npm run serve
configMCP_BINDMCP_AUTH_TOKEN=$(openssl rand -hex 32) =0.0.0.0 npm run serve
configMCP_BODY_LIMIT
configMCP_COMPUTE_GOVERNOR_MODE
configMCP_CSP_EXTRA_CONNECT
configMCP_DATASET_MAX_ACCESS_LEVEL
configMCP_HEALTH_REQUIRE_EMBEDDER
configMCP_LOG_LEVEL
configMCP_MEMORY_CONFIG_PATH3. Creates the config file with sensible defaults: ~/.mcp-memory/config.json (user scope) or <project>/.mcp-memory/config.json (project scope; the generated .mcp.json pins it via ).
configMCP_MEMORY_CWD
configMCP_MEMORY_DB_PATH"/abs/path/to/.mcp-memory/memory.db"
configMCP_MEMORY_DIMENSIONS384 Embedding vector dimensions. Must match the model's output.
configMCP_MEMORY_KEY_DIR
configMCP_MEMORY_MODELXenova/all-MiniLM-L6-v2 HuggingFace embedding model name. Must be an ONNX model compatible with Transformers.js.
configMCP_MEMORY_NLI_MODEL
configMCP_MEMORY_RERANKER_MODEL
configMCP_MEMORY_REVIEW_IN_PROGRESS
configMCP_MEMORY_SESSION_ID
configMCP_MEMORY_TRANSCRIPT_BASE
configMCP_METRICS_ENABLED
configMCP_PORT
configMCP_PUBLISH_ACCESS_LEVELS
configMCP_QUERY_SANITIZER
configMCP_RATELIMIT_DISABLED
configMCP_REDACT_MODE
configMCP_SIGN_MEMORIES
configMCP_TRUSTED_IP_HEADER
configMCP_TRUSTED_PUBKEYS
configMCP_VAULT_PATHvault path unset Obsidian vault root used by vault_sync, memory_export_vault, and rebuild when no explicit path is passed. and --vault <path> override.
configMCP_WEBHOOKSGET /api/webhooks List webhook targets (gated by )
configMCP_WEBHOOK_DISPATCH_INTERVAL_MS
configMEM_PER_CYCLE
configRERANK
configSCALE_DB
configSCALE_JSON
configSCALE_RERANK_ITERS
configSCALE_SEARCH_ITERS
configSCALE_SIZES
configSCALE_TIME_BUDGET_MS
// full audit trail
The full breakdown of what we checked, the deductions that landed, the network hosts, the dependency advisories, and concrete fix guidance is available to verified publishers.
// improvement guidance — verified publishers only
We have 2 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Score](https://m8ven.ai/badge/mcp/yonasvalentin-mcp-memory-graph-13dpb1)](https://m8ven.ai/mcp/yonasvalentin-mcp-memory-graph-13dpb1)
commit: dc6c4d85532cf8aaa4c14e1f34df53a0e444bb7c
code hash: 4762cd14505f68bed6c435c28e12d08ce0ba2709eef1cba872a2a15e86e92c63
verified: 6/17/2026, 11:25:04 AM
view raw JSON →