MCP server that builds a deterministic, source-traceable knowledge index of any codebase, enabling glossary lookup, code graphs, and exact-token search with every fact linked to its source file and line.
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.OPENMIND_EMBED_OFFLINE— 0 1 forces the deterministic hashing embedder (no model download).OPENMIND_DATA_DIR— ./data Where the learned index lives (SQLite + Chroma + map files).OPENMIND_ENRICH_EGRESS— 1 0 disables the audited Wikipedia enrichment lookup (fully offline).OPENMIND_SOURCELINK_EGRESSOPENMIND_MODELS_FOLDEROPENMIND_MODEL_PATHOPENMIND_LLAMA_SERVEROPENMIND_INGEST_FREE_GPU— 1 Briefly stop a managed model server during the embed pass to free VRAM for GPU embedding, then restart it.OPENMIND_EMBED_DEVICE— smart cpu · smart (GPU when the card is free, else CPU) · auto (always GPU if available) · gpu.OPENMIND_EMBED_BATCHOPENMIND_MACHINE_DIR— ~/.openmind Machine-local sidecar holding each project's absolute source root (kept outside data/ so the index stays portable).[](https://m8ven.ai/mcp/hellothisworld-open-mind-1gkt04)