A fully local RAG MCP server for semantic code search and code intelligence, using AST-level chunking and hybrid search to pinpoint functions, classes, and APIs. No cloud, no API keys, zero setup.
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.BASE_DIR— Set to the folder you want to search (BASE_DIRS for multiple roots — see [Configuration](#8-configuration-reference)).BASE_DIRS— Set BASE_DIR to the folder you want to search ( for multiple roots — see [Configuration](#8-configuration-reference)).CACHE_DIR— cache-dir ./models/ Model cache — recommend absolute pathCHUNK_MIN_LENGTH— ## 8.3 Minimum Chunk Length ()CODEX_HOMEDB_PATH— export =./my-dbHF_MODEL_REVISIONHTTPS_PROXY— With proxy () → direct to huggingface.coHTTP_PROXYMAX_FILE_SIZE— max-file-size 100 MB Max file size in bytesMODEL_NAME— model-name all-MiniLM-L6-v2 HuggingFace model IDRAG_DEVICE— ## 8.2 Execution Device ()RAG_DTYPE— controls ONNX precision (fp32 / fp16 / q8). Default fp32; use q8 when memory-constrained. ⚠️ Changing models or dtype requires deleting DB_PATH and re-indexing.RAG_INSTANCESRAG_WATCH— Set =true — the server starts recursive fs.watch on baseDirs (500ms debounce):[](https://m8ven.ai/mcp/damoqiongqiu-mcp-local-rag-1nlc37)