Provides semantic search across local files by creating vector embeddings from watched directories.
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.
Add to your MCP settings file:
{
"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:
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
~/Library/Application Support/Claude/claude_desktop_config.json
The server requires configuration through environment variables:
You must specify directories to watch using ONE of the following methods:
WATCH_DIRECTORIES
: Comma-separated list of directories to watchWATCH_CONFIG_FILE
: Path to a JSON configuration file with a watchList
arrayExample using WATCH_DIRECTORIES:
{
"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:
{
"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:
{
"watchList": [
"/path/to/dir1",
"/path/to/dir2",
"/path/to/specific/file.txt"
]
}
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 patternsExample with all optional parameters:
{
"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": []
}
}
}
This server provides the following MCP tools:
Perform semantic search across indexed files.
Parameters:
query
(required): The search query stringlimit
(optional): Maximum number of results to return (default: 5, max: 20)Example response:
[
{
"content": "matched text content",
"source": "/path/to/file",
"fileType": "markdown",
"score": 0.85
}
]
Get statistics about indexed files.
Parameters: None
Example response:
{
"totalDocuments": 42,
"watchedDirectories": ["/path/to/docs"],
"processingFiles": []
}
Search and retrieve cryptographic research papers from the IACR Cryptology ePrint Archive.
Web search using OpenAI's o3 model. Requires an OpenAI API key.
Enables LLMs to search, download, and extract information from YouTube music videos.
Fetches user data and event information from the Connpass platform using the Connpass and Gemini APIs.
Search for videos, users, and retrieve danmaku from the Bilibili API.
Integrates the RSS3 API to query the Open Web.
Get any answer from the Facebook Ads Library, conduct deep research including messaging, creative testing and comparisons in seconds.
Interact with the Haloscan SEO API for search engine optimization tasks.
Perform Google searches and view web content with advanced bot detection avoidance.
Provides comprehensive import and export trade data query functions, including trend analysis, product statistics, and geographic distribution.