MCP server providing semantic search over incident response knowledge from 23 authoritative security sources.
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.RAG_INDEX_DIR— ./data ChromaDB locationRAG_KNOWLEDGE_DIR— ./knowledge User documentsRAG_MODEL_NAME— BAAI/bge-base-en-v1.5 Embedding modelRAG_MAX_TOP_K— 50 Maximum top_k for queriesRAG_MAX_QUERY_LENGTH— 1000 Maximum query string lengthRAG_MAX_DOWNLOAD_BYTES— 62914560 (60MB) Maximum download size for network fetchesRAG_FETCH_MAX_RETRIES— 3 Max retries for transient network failuresRAG_ALLOW_HTTP— false Allow HTTP (not recommended; HTTPS enforced by default)RAG_UNSAFE_PATHSRAG_LOG_FORMAT— Settings are loaded via Config dataclass (config.py) with an explicit validate() method and global singleton caching in get_config(). Set =json for structured JSON logging.GITHUB_TOKEN— (optional) Higher API rate limits (see Security section)RAG_FETCH_RETRY_DELAY[](https://m8ven.ai/mcp/scriptedstatement-forensic-rag-mcp-f1ln80)