mcp-local-rag (xiuxiansk/mcp-local-rag) is an MCP server listed on the M8ven Trust Index. M8ven has not graded it: we have no way to read this server ourselves. No publisher has claimed this listing.
MCP server that enables local hybrid semantic and keyword search over private PDF, DOCX, Markdown, and text documents without sending data to embedding APIs.
Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. 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
xiuxiansk
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
M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.
BASE_DIRSet to that directory. It is also the security boundary for file operations. ReplaceBASE_DIRS(unset) JSON array of document roots; takes precedence over BASE_DIRCACHE_DIRcache-dir ./models/ Model cache directoryCHUNK_MIN_LENGTHchunk-min-length 50 Minimum chunk length in characters (1–10000)CODEX_HOMEDB_PATHsame directory so they use the same default index, or set BASE_DIR and explicitly.HF_MODEL_REVISIONMAX_FILE_SIZEmax-file-size 104857600 (100MB) Maximum file size in bytesMODEL_NAMEboth interfaces should share an index. In particular, and the CLI --model-nameRAG_BATCH_SIZERAG_DEVICEcpu ONNX Runtime execution deviceRAG_DTYPEfp32 Embedding dtype supplied by the selected modelTool 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
18/18 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), +15 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 test coverage
6/18 tools referenced in tests (33%)
Write tests that reference each tool by name so every tool has at least one test.
Shell command execution
2 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
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/xiuxiansk-mcp-local-rag-1warpl)?variant=verified to the badge 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