https://github.com/lishenxydlgzs/simple-files-vectorstore
A simple vector store that indexes content of files on local file system
https://github.com/lishenxydlgzs/simple-files-vectorstore
Last synced: 6 months ago
JSON representation
A simple vector store that indexes content of files on local file system
- Host: GitHub
- URL: https://github.com/lishenxydlgzs/simple-files-vectorstore
- Owner: lishenxydlgzs
- License: mit
- Created: 2025-02-02T23:45:37.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-03-31T17:23:28.000Z (6 months ago)
- Last Synced: 2025-04-16T00:57:31.054Z (6 months ago)
- Language: TypeScript
- Size: 201 KB
- Stars: 16
- Watchers: 1
- Forks: 1
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- mcp-index - Files Vector Store - Creates a vector store from local directories and files, enabling semantic search across document contents. Monitors specified directories for file changes and generates vector embeddings to facilitate search functionality. (Data Analytics)
README
# @lishenxydlgzs/simple-files-vectorstore
A Model Context Protocol (MCP) server that provides semantic search capabilities across files. This server watches specified directories and creates vector embeddings of file contents, enabling semantic search across your documents.
## Installation & Usage
Add to your MCP settings file:
```json
{
"mcpServers": {
"files-vectorstore": {
"command": "npx",
"args": [
"-y",
"@lishenxydlgzs/simple-files-vectorstore"
],
"env": {
"WATCH_DIRECTORIES": "/path/to/your/directories"
},
"disabled": false,
"autoApprove": []
}
}
}
```
MCP settings file locations:
- VSCode Cline Extension: `~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json`
- Claude Desktop App: `~/Library/Application Support/Claude/claude_desktop_config.json`
## Configuration
The server requires configuration through environment variables:
### Required Environment Variables
You must specify directories to watch using ONE of the following methods:
- `WATCH_DIRECTORIES`: Comma-separated list of directories to watch
- `WATCH_CONFIG_FILE`: Path to a JSON configuration file with a `watchList` array
Example using WATCH_DIRECTORIES:
```json
{
"mcpServers": {
"files-vectorstore": {
"command": "npx",
"args": [
"-y",
"@lishenxydlgzs/simple-files-vectorstore"
],
"env": {
"WATCH_DIRECTORIES": "/path/to/dir1,/path/to/dir2"
},
"disabled": false,
"autoApprove": []
}
}
}
```
Example using WATCH_CONFIG_FILE:
```json
{
"mcpServers": {
"files-vectorstore": {
"command": "npx",
"args": [
"-y",
"@lishenxydlgzs/simple-files-vectorstore"
],
"env": {
"WATCH_CONFIG_FILE": "/path/to/watch-config.json"
},
"disabled": false,
"autoApprove": []
}
}
}
```
The watch config file should have the following structure:
```json
{
"watchList": [
"/path/to/dir1",
"/path/to/dir2",
"/path/to/specific/file.txt"
]
}
```
### Optional Environment Variables
- `CHUNK_SIZE`: Size of text chunks for processing (default: 1000)
- `CHUNK_OVERLAP`: Overlap between chunks (default: 200)
- `IGNORE_FILE`: Path to a .gitignore style file to exclude files/directories based on patterns
Example with all optional parameters:
```json
{
"mcpServers": {
"files-vectorstore": {
"command": "npx",
"args": [
"-y",
"@lishenxydlgzs/simple-files-vectorstore"
],
"env": {
"WATCH_DIRECTORIES": "/path/to/dir1,/path/to/dir2",
"CHUNK_SIZE": "2000",
"CHUNK_OVERLAP": "500",
"IGNORE_FILE": "/path/to/.gitignore"
},
"disabled": false,
"autoApprove": []
}
}
}
```
## MCP Tools
This server provides the following MCP tools:
### 1. search
Perform semantic search across indexed files.
Parameters:
- `query` (required): The search query string
- `limit` (optional): Maximum number of results to return (default: 5, max: 20)
Example response:
```json
[
{
"content": "matched text content",
"source": "/path/to/file",
"fileType": "markdown",
"score": 0.85
}
]
```
### 2. get_stats
Get statistics about indexed files.
Parameters: None
Example response:
```json
{
"totalDocuments": 42,
"watchedDirectories": ["/path/to/docs"],
"processingFiles": []
}
```
## Features
- Real-time file watching and indexing
- Semantic search using vector embeddings
- Support for multiple file types
- Configurable chunk size and overlap
- Background processing of files
- Automatic handling of file changes and deletions
## Repository
[GitHub Repository](https://github.com/lishenxydlgzs/simple-files-vectorstore)