RAG Vault
RAG Vault lets your AI coding assistant search your private documents locally. Everything runs on your machine and your data stays private.
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
RobThePCGuy
Source: Glama
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. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
query_documentsSearch your documents using both meaning and exact keyword matching. You can also use advanced syntax: - "exact phrase" → Match phrase exactly - field:value → Filter by custom metadata (e.g., domain:legal, author:john) - term1 AND term2 → Both terms required (default) - term1 OR term2 → Either term …
ingest_fileAdd a document (PDF, DOCX, TXT, MD, JSON, JSONL) to your knowledge base so you can search it. Use the full file path. If you ingest the same file again, it replaces the old version. You can tag it with metadata like author, domain, or tags.
ingest_dataAdd text content directly instead of from a file. Good for: fetched web pages (format: html), copied text (format: text), or markdown strings (format: markdown). The source identifier lets you update the content later by re-ingesting with the same source. You can add custom metadata too. For files o…
delete_fileRemove a document from your knowledge base. Use filePath for files you added with ingest_file, or source for content you added with ingest_data. You need to provide one or the other.
list_filesShow all documents in your knowledge base, with file paths and how many chunks each one has.
statusCheck how many documents and chunks you have, the database size, and current settings.
feedback_pinMark a search result as relevant for a query. Pinned results get boosted in future searches. Use this when a result was helpful.
feedback_dismissMark a search result as irrelevant for a query. Dismissed results get pushed down in future searches. Use this when a result wasn't helpful.
feedback_statsSee your feedback stats: total events, how many results you've pinned, and how many you've dismissed.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
Multer Vulnerable to Denial of Service via Uncontrolled Recursion
Multer vulnerable to Denial of Service via deeply nested field names
Multer vulnerable to Denial of Service via resource exhaustion
Multer vulnerable to Denial of Service via incomplete cleanup
ALLOWED_SCAN_ROOTSHome directory Directories allowed for database scanningBASE_DIR2. Pick a documents directory and set to that path.CACHE_DIR"": "./.cache",CODEX_HOMECORS_ORIGINSlocalhost Allowed origins (comma-separated, or )DB_PATH"": "./documents/.rag-db",EMBEDDER_INIT_TIMEOUT_MSJSON_BODY_LIMIT5mb Max request body sizeMAX_FILE_SIZE104857600 (100 MB) Biggest file you can ingestMCP_CONNECT_TIMEOUT_MSMODEL_NAMEXenova/all-MiniLM-L6-v2 HuggingFace embedding modelRAG_API_KEYAPI Authentication: Optional API key viaRAG_EMBEDDING_DEVICE"": "cpu",RAG_GROUPING"": "related"RAG_HYBRID_WEIGHT"": "0.6",RAG_HYDE_API_BASE_URLRAG_HYDE_API_KEYunset API key for LLM backend (required when RAG_HYDE_BACKEND=api)RAG_HYDE_API_MODELclaude-haiku-4-5-20251001 Model for LLM-based expansionRAG_HYDE_BACKENDrule-based rule-based for local template expansion, api for LLM-based HyDERAG_HYDE_ENABLEDfalse Turn on query expansion for better recallRAG_HYDE_EXPANSIONS2 Number of expanded queries to generateRAG_MAX_DISTANCEunset Drops results below this relevance threshold (use with boost mode; rrf scores are rank-based)RAG_RERANKER_CANDIDATE_MULTIPLIER2 Fetch this many extra candidates for the reranker to scoreRAG_RERANKER_DEVICEauto Device for the reranker (same options as RAG_EMBEDDING_DEVICE)RAG_RERANKER_ENABLEDfalse Turn on cross-encoder reranking for better resultsRAG_RERANKER_MODELXenova/ms-marco-MiniLM-L-6-v2 HuggingFace cross-encoder model (~23MB ONNX, downloads on first use)RAG_RRF_K60 RRF smoothing constant (only applies in rrf mode). Industry standard is 60.RAG_SEARCH_MODEboost Fusion mode: boost (multiplicative keyword boost) or rrf (Reciprocal Rank Fusion)RATE_LIMIT_MAX_REQUESTS100 Max requests per windowRATE_LIMIT_WINDOW_MS60000 Rate limit time window (ms)REQUEST_LOGGINGfalse Turn on request audit loggingREQUEST_TIMEOUT_MS30000 API request timeoutRERANKER_INIT_TIMEOUT_MS600000 (10 min) Timeout for model download and initializationUPLOAD_DIR./uploads/ Temporary directory for web UI file uploadsVECTORSTORE_INIT_TIMEOUT_MSWEB_PORT3000 Port for web interfaceTool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
9/9 tools missing one or more hints — query_documents (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ingest_file (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); ingest_data (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +6 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
Only 0/9 tool handlers declare input schemas (0%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool test coverage
6/9 tools referenced in tests (67%)
Write tests that reference each tool by name so every tool has at least one test.
Production dependencies are patched
0 critical, 5 high severity in production deps — multer@2.0.2 (high), multer@2.0.2 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/robthepcguy/rag-vault)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check