Package
mcp-local-rag
Easy-to-setup local RAG server with minimal configuration
io.github.shinpr/mcp-local-ragSource repository
Overview
What this server provides
Easy-to-setup local RAG server with minimal configuration
Install
1Packages
mcp-local-rag0.19.0
Runtime
Not declaredTransport stdio- BASE_DIROptional
Base directory for document storage (defaults to current working directory). Ignored when BASE_DIRS is set.
Format: string - BASE_DIRSOptional
JSON array of base directories (e.g. '["/a","/b"]'). Takes precedence over BASE_DIR.
Format: string - DB_PATHOptional
Path to LanceDB database directory (defaults to ./lancedb/)
Format: string - CACHE_DIROptional
Directory where Transformers.js models are cached (defaults to ./models/)
Format: string - HF_ENDPOINTOptional
Hugging Face model download endpoint. Set this to a mirror URL when direct downloads are blocked (defaults to https://huggingface.co).
Format: string - MODEL_NAMEOptional
Embedding model name (defaults to Xenova/all-MiniLM-L6-v2)
Format: string - MAX_FILE_SIZEOptional
Maximum file size in bytes (defaults to 104857600 / 100MB)
Format: string - RAG_MAX_DISTANCEOptional
Maximum distance threshold for filtering search results. Results with distance greater than this value will be excluded. Lower values mean stricter filtering (e.g., 0.5 for high relevance only)
Format: string - RAG_GROUPINGOptional
Grouping mode for quality filtering. 'similar' returns only the most similar group (stops at first distance jump). 'related' includes related groups (stops at second distance jump). Unset means no grouping filter
Format: string - RAG_MAX_FILESOptional
Maximum number of files to keep in search results. Results are filtered to include only chunks from the top N best-scoring files. For example, 1 returns only the single best-matching file's chunks. Unset means no file filtering.
Format: string - CHUNK_MIN_LENGTHOptional
Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion.
Format: string - STORE_IMAGESOptional
Store supported PDF and DOCX images during ingestion and return them with matched chunks (defaults to false).
Format: string - RAG_DEVICEOptional
Execution device for the embedder (defaults to cpu). Passed straight to ONNX Runtime; see the Transformers.js device source for the supported backend names. If the requested device fails to initialize, the server throws an error.
Format: string - RAG_DTYPEOptional
Embedding quantization dtype for the embedder (defaults to fp32). Opt-in and pass-through; accepts any dtype the chosen model provides (fp32, fp16, q8, int8, ...). If the model has no variant for the requested dtype, the server throws an error. Changing this changes the embedding space — re-ingest existing data.
Format: string - RAG_HYBRID_WEIGHTOptional
Keyword boost factor for hybrid search (0.0-1.0, defaults to 0.6). 0 means semantic similarity only; higher values increase the keyword-match contribution to the final score.
Format: string - RAG_RERANK_CMDOptional
External command that reorders query_documents results (unset disables reranking). The search query and the matched document chunks, including their text, are passed to this command, so a command that contacts a remote service sends that content off this machine.
Format: string - RAG_RERANK_TIMEOUT_MSOptional
Time budget per rerank call in milliseconds (100-600000, defaults to 10000). On timeout the spawned command is killed and the pre-rerank ordering is returned.
Format: string