get_index_status
Get status information about the current search index.
Returns total chunks, list of indexed files with chunk counts, and file type distribution.
LABSCO SUMMARY
Five hundred documents you can ask questions of, with nothing leaving the machine.
It indexes what is already on your disk and returns the relevant passages, so the assistant answers from your contracts and reports instead of from its training data. After the one-time model download there are no network calls at all.
What it is
A local semantic index over a folder of documents — txt, md, pdf, docx, pptx, csv — stored as LanceDB files on disk and searched in natural language.
What you get
- A folder indexed or re-indexed, with the supported document types picked up automatically
- Natural-language search that returns the relevant chunks, not whole files
- Hybrid search: semantic similarity combined with full-text keyword search via Reciprocal Rank Fusion
- Incremental indexing by content hash — only changed files are reprocessed
- Index status: total chunks and which files are in it, with their chunk counts
- A single file forced back through indexing, ignoring the hash cache
- 50+ languages, including asking in one language and finding results in another
- Fully offline after a one-time model download
Requirements
Python 3.11 or newer, and room on disk for the index and the embedding model (about 120 MB, downloaded once). LanceDB keeps everything as local files, so there is no server, container or database to run, and no API key.
Setup effort
Build from source — git clone https://github.com/ZhuBit/cowork-semantic-search.git
USE CASES
01
Finding the document that answers a question
Ask in plain language and get the matching chunks back, ranked by both meaning and keyword.
02
Getting a folder of reports ready to search
Index it once; re-indexing later only reprocesses the files whose contents actually changed.
03
Searching notes written in another language
The embeddings cover 50+ languages, so an English question can surface a German passage.
04
Picking up a file you just edited
Force that one file through indexing rather than waiting for the next full pass.
05
Checking what is actually in the index
Total chunks and the per-file breakdown show whether the document you expected was ever picked up.
4 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
index_folder
Index or re-index all documents in a folder for semantic search.
Scans the folder for supported document types (.txt, .md, .pdf, .docx, .pptx, .csv), extracts text, splits into chunks, computes embeddings, and stores them in a local vector database. Only processes files that have changed since the last indexing run. Safe to call multiple times — unchanged files are skipped automatically.
reindex_file
Force re-index a single file, ignoring the content hash cache.
Deletes existing chunks for this file, re-parses, re-chunks, re-embeds, and stores new chunks. Useful when you know a file has changed or when parsing was updated.
semantic_search
Search indexed documents using natural language.
Finds the most relevant document chunks matching the query using semantic similarity. Returns ranked results with source file paths and relevance scores.
Use mode='hybrid' to combine vector search with full-text search via Reciprocal Rank Fusion for better keyword + semantic matching.
The folder must be indexed first with index_folder.
BEFORE YOU INSTALL
What to know first
Tools you get
4 tools when we connected.
Requires
Python 3.11+
Where it runs
All 4 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 4 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/ZhuBit/cowork-semantic-search.git
cd cowork-semantic-search
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[all]"MCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"semantic-search": {
"command": "<YOUR_PATH_TO_VENV>/bin/python",
"args": [
"-m",
"server.main"
],
"cwd": "<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH>",
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH>"
}
}
}
}Goes in .mcp.json in your project root. <YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH> is the folder you cloned, and point command at the .venv/bin/python inside that folder (the virtual environment created during installation).
Cursor
CURSOR · JSON
{
"mcpServers": {
"semantic-search": {
"command": "<YOUR_PATH_TO_VENV>/bin/python",
"args": [
"-m",
"server.main"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH>"
}
}
}
}Goes in .cursor/mcp.json in your project root, or ~/.cursor/mcp.json globally. <YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH> is the folder you cloned, and point command at the .venv/bin/python inside that folder (the virtual environment created during installation).
Windsurf
WINDSURF · JSON
{
"mcpServers": {
"semantic-search": {
"command": "<YOUR_PATH_TO_VENV>/bin/python",
"args": [
"-m",
"server.main"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH>"
}
}
}
}Goes in ~/.codeium/windsurf/mcp_config.json. <YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH> is the folder you cloned, and point command at the .venv/bin/python inside that folder (the virtual environment created during installation).
Cline
Open Cline > MCP Servers icon > Configure > Advanced MCP Settings, then add:
CLINE · JSON
{
"mcpServers": {
"semantic-search": {
"command": "<YOUR_PATH_TO_VENV>/bin/python",
"args": [
"-m",
"server.main"
],
"env": {
"PYTHONPATH": "<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH>"
}
}
}
}<YOUR_PATH_TO_COWORK_SEMANTIC_SEARCH> is the folder you cloned, and point command at the .venv/bin/python inside that folder (the virtual environment created during installation).
