searchLABSCO SUMMARY
Semantic search over your own folders, with no service to sign up for.
The watcher is what makes it worth wiring in permanently: edit a file and the next search sees the new version, so the index does not go stale between sessions. Results come back with the source path attached, which is what lets the assistant quote and then go read the rest.
What it is
A server that watches directories, embeds file contents into a vector store, and answers semantic queries over them.
What you get
- search — semantic search across the indexed files, returning the matched text, the source path, the file type and a score
- get_stats — how many documents are indexed, which directories are watched, and what is still processing
- Files re-indexed as they change, and removed from the index when deleted
- Chunking you control: CHUNK_SIZE defaults to 1000 and CHUNK_OVERLAP to 200
- IGNORE_FILE takes a .gitignore-style file to keep directories out of the index
Requirements
npx and the @lishenxydlgzs/simple-files-vectorstore package. You must set one of WATCH_DIRECTORIES, a comma-separated list of paths, or WATCH_CONFIG_FILE, pointing at a JSON file with a watchList array — the server has nothing to index otherwise. No account or key. search takes a limit that defaults to 5 and caps at 20.
Setup effort
One command — npx -y @lishenxydlgzs/simple-files-vectorstore
USE CASES
01
Finding a document when you cannot remember the words in it
Search by what it was about; matches come back with the file path and a score.
02
Answering questions from a folder of project docs
Watch the directory and let the assistant retrieve the relevant passages before it answers.
03
Checking the index is actually current
Read back the document count, the watched directories, and anything still being processed.
04
Keeping build output and dependencies out of the index
Point IGNORE_FILE at a .gitignore-style file so those paths are never embedded.
05
Tuning retrieval on long documents
Raise the chunk size and overlap so a passage does not get cut in half.
2 tools
Listed in project docs. Your client may show a different list.
get_statsBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
npx on PATH
Where it runs
Both documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npx -y @lishenxydlgzs/simple-files-vectorstoreMCP Clients
Cline, Claude Desktop
JSON
{
"mcpServers": {
"files-vectorstore": {
"command": "npx",
"args": [
"-y",
"@lishenxydlgzs/simple-files-vectorstore"
],
"env": {
"WATCH_DIRECTORIES": "<YOUR_WATCH_DIRECTORIES>"
},
"disabled": false,
"autoApprove": []
}
}
}
