Provides persistent, semantic, cross-session memory for coding agents, backed by Microsoft Memora.
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.MEMORA_MCP_HOME— ~/.memora-mcp Store + config location.MEMORA_SRC— The server finds Memora automatically at ~/.memora-mcp/Memora/src, or set =/path/to/Memora/src.OPENAI_API_TYPEOPENAI_API_KEY— export =sk-... # or a gateway keyMEMORA_LLM_MODEL— cheap per plane Extraction model — haiku (Claude) / gpt-4.1-mini (API). Set sonnet, gpt-5, etc. for sharper memories.AZURE_OPENAI_ENDPOINTAZURE_OPENAI_API_VERSIONMEMORA_EMBEDDING_MODELAZURE_MANAGED_IDENTITY_CLIENT_IDMEMORA_EMBEDDING— local local (in-process, no key) or api (a served endpoint you opt into).MEMORA_UPDATE_THRESHOLDMEMORA_HYBRIDMEMORA_EPISODICMEMORA_MCP_USER— $USER Selects the per-user collection.MEMORA_PLANE— auto Force the model plane: subscription-claude, subscription-codex, api, or auto-detect.OPENAI_BASE_URL— export =https://... # OpenAI, Azure, LiteLLM, vLLM, Databricks AI GatewayMEMORA_REASONING— low Reasoning/effort for extraction. low is plenty for this task.MEMORA_DISTILL_TIMEOUTMEMORA_CAPTURE— rich How much to store: lean · balanced · rich (store more, trust recall).MEMORA_MIN_TURNS— 3 Skip capturing sessions shorter than this.MEMORA_MAX_DISTILLS_PER_DAY— 300 Write-cap safety valve.MEMORA_SESSION_SUMMARY— 1 Also store a short episodic summary of each session.MEMORA_RECALL_LINESMEMORA_RECALL_BYTES[](https://m8ven.ai/mcp/trwilcoxson-memora-mcp-l86z59)