Skip to content

History of MCP server in namespace io.github

io.github.shinpr/mcp-local-rag · Status: active

The source provides no name of its own for this entry. The identifier therefore appears on this page as a coordinate, not as the heading.

If you find your own account name here: write informally to German.saas@web.de, stating the identifier concerned. No reason has to be given. How to object

Every published change to this entry, most recent first.

Changes
2026-08-24Version: 0.17.4 → 0.18.0
2026-08-24Last changed in the registry (raw): 2026-08-12 → 2026-08-23
2026-08-24First listed in the registry (raw): 2026-08-12 → 2026-08-23
2026-08-24Environment variable descriptions (raw): BASE_DIR=Base directory for document storage (defaults to current working directory). Ignored when BASE_DIRS is set. · BASE_DIRS=JSON array of base directories (e.g. '["/a","/b"]'). Takes precedence over BASE_DIR. · CACHE_DIR=Directory where Transformers.js models are cached (defaults to ./models/) · CHUNK_MIN_LENGTH=Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion. · DB_PATH=Path to LanceDB database directory (defaults to ./lancedb/) · MAX_FILE_SIZE=Maximum file size in bytes (defaults to 104857600 / 100MB) · MODEL_NAME=Embedding model name (defaults to Xenova/all-MiniLM-L6-v2) · RAG_DEVICE=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. · RAG_DTYPE=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. · RAG_GROUPING=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 · RAG_HYBRID_WEIGHT=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. · RAG_MAX_DISTANCE=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) · RAG_MAX_FILES=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. → BASE_DIR=Base directory for document storage (defaults to current working directory). Ignored when BASE_DIRS is set. · BASE_DIRS=JSON array of base directories (e.g. '["/a","/b"]'). Takes precedence over BASE_DIR. · CACHE_DIR=Directory where Transformers.js models are cached (defaults to ./models/) · CHUNK_MIN_LENGTH=Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion. · DB_PATH=Path to LanceDB database directory (defaults to ./lancedb/) · MAX_FILE_SIZE=Maximum file size in bytes (defaults to 104857600 / 100MB) · MODEL_NAME=Embedding model name (defaults to Xenova/all-MiniLM-L6-v2) · RAG_DEVICE=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. · RAG_DTYPE=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. · RAG_GROUPING=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 · RAG_HYBRID_WEIGHT=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. · RAG_MAX_DISTANCE=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) · RAG_MAX_FILES=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. · STORE_IMAGES=Store supported PDF and DOCX images during ingestion and return them with matched chunks (defaults to false).
2026-08-24Package versions (raw): 0.17.4 → 0.18.0
2026-08-24Environment variables (raw): BASE_DIR, BASE_DIRS, DB_PATH, CACHE_DIR, MODEL_NAME, MAX_FILE_SIZE, RAG_MAX_DISTANCE, RAG_GROUPING, RAG_MAX_FILES, CHUNK_MIN_LENGTH, RAG_DEVICE, RAG_DTYPE, RAG_HYBRID_WEIGHT → BASE_DIR, BASE_DIRS, DB_PATH, CACHE_DIR, MODEL_NAME, MAX_FILE_SIZE, RAG_MAX_DISTANCE, RAG_GROUPING, RAG_MAX_FILES, CHUNK_MIN_LENGTH, STORE_IMAGES, RAG_DEVICE, RAG_DTYPE, RAG_HYBRID_WEIGHT
2026-08-16Last changed in the registry (raw): – → 2026-08-12
2026-08-16First listed in the registry (raw): – → 2026-08-12
2026-08-16Registry status message (raw): – → –
2026-08-16Schema version of the raw record (raw): – → https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json
2026-08-16Icon formats (raw): – → –
2026-08-16Environment variable descriptions (raw): – → BASE_DIR=Base directory for document storage (defaults to current working directory). Ignored when BASE_DIRS is set. · BASE_DIRS=JSON array of base directories (e.g. '["/a","/b"]'). Takes precedence over BASE_DIR. · CACHE_DIR=Directory where Transformers.js models are cached (defaults to ./models/) · CHUNK_MIN_LENGTH=Minimum chunk length in characters (1-10000, defaults to 50). Chunks shorter than this threshold are filtered out during ingestion. · DB_PATH=Path to LanceDB database directory (defaults to ./lancedb/) · MAX_FILE_SIZE=Maximum file size in bytes (defaults to 104857600 / 100MB) · MODEL_NAME=Embedding model name (defaults to Xenova/all-MiniLM-L6-v2) · RAG_DEVICE=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. · RAG_DTYPE=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. · RAG_GROUPING=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 · RAG_HYBRID_WEIGHT=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. · RAG_MAX_DISTANCE=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) · RAG_MAX_FILES=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.
2026-08-16Environment variable formats (raw): – → string
2026-08-16Delivery form (raw): – → paket
2026-08-16Remote hosts (raw): – → –
2026-08-16Remote URLs (raw): – → –
2026-08-16Runtime hints (raw): – → –
2026-08-16Package versions (raw): – → 0.17.4
2026-08-16Package identifiers (raw): – → mcp-local-rag
2026-08-16Repository subfolder (raw): – → –
2026-08-16Repository platform (raw): – → github
2026-08-16Path environment variables (raw): – → –
2026-08-16Required secret headers (raw): – → –
2026-08-13Version: 0.17.3 → 0.17.4
2026-08-06Version: – → 0.17.3
2026-08-06Repository URL listed: – → true
2026-08-06Path argument present: – → false
2026-08-06Execution location: – → local
2026-08-06Credentials required: – → false
2026-08-06Package registries (raw): – → npm
2026-08-06Repository (raw): – → https://github.com/shinpr/mcp-local-rag
2026-08-06Path arguments (raw): – → –
2026-08-06Transports (raw): – → stdio
2026-08-06Required secret variables (raw): – → –
2026-08-06Environment variables (raw): – → BASE_DIR, BASE_DIRS, DB_PATH, CACHE_DIR, MODEL_NAME, MAX_FILE_SIZE, RAG_MAX_DISTANCE, RAG_GROUPING, RAG_MAX_FILES, CHUNK_MIN_LENGTH, RAG_DEVICE, RAG_DTYPE, RAG_HYBRID_WEIGHT

tracevero · https://tracevero.com/mcp/io-github-shinpr-mcp-local-rag/aenderungen