A self-hosted, notebook-scoped RAG pipeline with contextual retrieval, delivered as an MCP server. Enables ingestion of documents into named notebooks and semantic search returning raw ranked chunks.
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.SCRIBBLESLM_HOMESCRIBBLESLM_DB_PATHSCRIBBLESLM_MODELS_DIRVOYAGE_API_KEY— then edit ~/.scribbleslm/.env and set =<your key>VOYAGE_MODEL— Public embeddings (Voyage): model is configurable via (defaultVOYAGE_FALLBACK_MODELVOYAGE_CONCURRENCYVOYAGE_TPM_CEILINGPRIVATE_EMBEDDING_MODEL_PATH— private path default ~/.scribbleslm/models/bge-m3-Q5_K_M.ggufPRIVATE_EMBEDDING_THREADSCONTEXT_LLM_BASE_URL— is only the default example. Point / CONTEXT_LLM_API_KEY /CONTEXT_LLM_API_KEY— is only the default example. Point CONTEXT_LLM_BASE_URL / /CONTEXT_LLM_MODEL— at any provider (OpenAI, OpenRouter, a self-hosted vLLM or OllamaDEFAULT_PRIVATE— The default is set by . Queries are guarded the same way: a query you flagPROFILE_CACHE_DIRPROFILE_SYNTHESISSCRIBBLESLM_DOCUMENTS_ROOTSCRIBBLESLM_MAX_DOCUMENT_BYTESRERANKER_ENABLED— no default false (reranker off)RERANKER_MODELRERANKER_IDLE_EXITVOYAGE_RERANK_MODEL[](https://m8ven.ai/mcp/elphamale-scribbleslm-13s56y)