Enables automatic knowledge capture and injection of guardrails for AI assistants like Claude and Cursor, improving code quality and preventing recurring mistakes.
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.API_PORTBACKUP_EXCLUDE_PROJECTS— (comma-separated, in .env, never committed) removes specific projects from the export before it's written/committed:BRAIN_API_URLBRAIN_AUTO_BACKUP— Turn off auto-backup: =false.BRAIN_HOOK_CWDBRAIN_HOOK_SESSION_IDBRAIN_HOOK_SOURCEBRAIN_HOOK_TRANSCRIPT_PATHCHROMA_COLLECTIONCHROMA_URLCLASSIFIER_ENABLED— true # false disables it without touching codeCLASSIFIER_LANGUAGE— en # language of generated content (title/content/directive/reasoning) — defaults to "en" if omittedCLASSIFIER_TIMEOUT_MS— 60000 # real observed latency: 2-20sCONSOLIDATE_THRESHOLD— 1. Embeds all active solution items and clusters them by cosine similarity (union-find, threshold configurable via , default 0.80).OLLAMA_API_KEY— cp .env.example .env # 1. local config ( is optional — without it, the classifier stays pending_review)OLLAMA_CLOUD_MODEL— qwen3-coder:480b-cloudOLLAMA_FALLBACK_MODELS— minimax-m2.1:cloud # optional, comma-separatedOLLAMA_MODELOLLAMA_URLSQLITE_PATH[](https://m8ven.ai/mcp/guilopes29-brain-mcp-1gaon1)