Enables semantic code search across multiple repositories using AST-aware chunking and relationship tracking. Supports local LLM embeddings, real-time indexing, and cross-codebase dependency analysis through vector and graph databases.
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.LOG_LEVEL— INFO Logging levelWORKSPACE_PATH— /workspace Path to mounted codebaseREPO_NAMEQDRANT_HOST— qdrant Qdrant server hostnameQDRANT_PORT— 6333 Qdrant server portOLLAMA_HOST— export =http://localhost:11434EMBEDDING_MODEL— embeddinggemma:latest Ollama embedding model to useINDEX_PATH— /index Path for index metadataCACHE_PATH— /cache Path for embedding cacheMAX_CHUNK_SIZE— 2048 Maximum chunk size in charactersBATCH_SIZE— 32 Embedding batch sizeMAX_CONCURRENT_EMBEDDINGS— 4 Concurrent embedding requestsINCREMENTALENABLE_GRAPH_DB— false Enable Neo4j graph databaseNEO4J_URI— bolt://neo4j:7687 Neo4j connection URINEO4J_USER— neo4j Neo4j usernameNEO4J_PASSWORD— password Neo4j passwordEXCLUDE_PATTERNSLOG_FILEENABLE_FILE_WATCHER— true Enable real-time file watchingWATCHER_DEBOUNCE_SECONDS— 2.0 Delay before processing file changes[](https://m8ven.ai/mcp/jarmentor-codebase-contextifier-9000-xxjsyj)