A semantic retrieval system that gives AI assistants on-demand access to domain-specific governance principles — a queryable 'second brain' of encoded standards.
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.ENABLE_BACKEND_ACCESS_CONTROLCOGNEE_SKIP_CONNECTION_TESTAI_CONTEXT_ENGINE_COGNEE_LLM_PROVIDER— export =ollama # 'ollama', 'anthropic', 'openai'AI_CONTEXT_ENGINE_COGNEE_LLM_MODEL— export = # provider-dependent model nameAI_CONTEXT_ENGINE_COGNEE_LLM_API_KEY— export = # required for cloud providersAI_CONTEXT_ENGINE_COGNEE_LLM_ENDPOINT— export = # custom endpoint (non-default Ollama port, Azure, OpenAI-compatible)AI_CONTEXT_ENGINE_COGNEE_LLM_TEMPERATURE— export = # LLM temperature (default: 0.0; >0 may produce non-reproducible entity graphs)AI_CONTEXT_ENGINE_EMBEDDING_MODEL— export =BAAI/bge-small-en-v1.5AI_CONTEXT_ENGINE_EMBEDDING_DIMENSIONS— export =384AI_CONTEXT_ENGINE_EMBED_SOCKETAI_CONTEXT_ENGINE_LOG_LEVELAI_CONTEXT_ENGINE_READONLY— export =auto # 'true', 'false', or 'auto' (sandbox detection)AI_CONTEXT_ENGINE_SEMANTIC_WEIGHT— export =0.7AI_CONTEXT_ENGINE_INDEX_PATH— export =~/.context-engine/indexesAI_CONTEXT_ENGINE_INDEX_MODE— export =realtime # 'ondemand' or 'realtime' (file watcher)AI_CONTEXT_ENGINE_DEFAULT_PROJECTAI_CONTEXT_ENGINE_WATCHER_MAX_UPTIME_HOURSGOVERNANCE_ENFORCEMENT_ENABLED— true Master toggleGOVERNANCE_ENFORCEMENT_SOFT_MODE— Structural (hard) Set =false ~100% (blocks action tools) Production workflowsGOVERNANCE_RECENCY_WINDOW— 50 Tool calls before governance expiresGOVERNANCE_STATE_FILEGOVERNANCE_STATE_TTLAI_GOVERNANCE_MCP_PROJECT[](https://m8ven.ai/mcp/jason21wc-ai-governance-mcp-1884iq)