Connection check
local install
rag-vault
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
Tools
9
GitHub stars
2
Installs / wk
210
Licence
—
Transport
stdio
Last checked
never
Tools & capabilities
9 toolsRead from the published package source — this server runs locally, so there is no endpoint to query. Names are taken from the code, not observed at runtime, and descriptions are often absent.
delete_file
from source
Remove 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 othe… Remove 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.
feedback_dismiss
from source
Mark a search result as irrelevant for a query. Dismissed results get pushed down in future searches. Use this when a result wasn Mark a search result as irrelevant for a query. Dismissed results get pushed down in future searches. Use this when a result wasn
feedback_pin
from source
Mark a search result as relevant for a query. Pinned results get boosted in future searches. Use this when a result was helpful. Mark a search result as relevant for a query. Pinned results get boosted in future searches. Use this when a result was helpful.
feedback_stats
from source
See your feedback stats: total events, how many results you See your feedback stats: total events, how many results you
ingest_data
from source
Add 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 identif… Add 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 on disk, use ingest_file instead.
ingest_file
from source
Add 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… Add 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.
list_files
from source
Show all documents in your knowledge base, with file paths and how many chunks each one has. Show all documents in your knowledge base, with file paths and how many chunks each one has.
query_documents
from source
Search your documents using both meaning and exact keyword matching. You can also use advanced syntax: - Search your documents using both meaning and exact keyword matching. You can also use advanced syntax: -
status
from source