folder_stats
Provides a tool to count files and folders in a directory, supporting both recursive and non-recursive counts.
README
Local MCP: Folder/File Counter
This is a simple Model Context Protocol (MCP) server written in Python using the official mcp SDK (specifically FastMCP). It provides a single tool called get_folder_stats that allows LLMs to retrieve the number of files and folders within a given directory, both recursively and non-recursively.
Features
- Non-recursive count (default): Lists and counts files and subdirectories directly inside the target path.
- Recursive count (optional): Counts all files and folders in nested subdirectories when
recursive=true. - Error handling: Returns clear JSON error messages for invalid paths, missing directories, or permission issues.
Setup Instructions
-
Install dependencies: Make sure you have Python installed, then install the required
mcppackage:pip install -r requirements.txt -
Test the server (optional): You can run the server directly to make sure it executes without errors. It will wait for MCP JSON-RPC messages via standard input/output.
python server.py(Press
Ctrl+Cto exit)
Registering with Claude Desktop
To use this tool locally with Claude, you need to add it to your Claude Desktop configuration.
- Open your Claude Desktop config file:
- Windows:
%APPDATA%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
- Add the following entry to your
mcpServersobject. ReplaceYOUR_ABSOLUTE_PATHwith the full path to where you saved this project.
{
"mcpServers": {
"folder_stats": {
"command": "python",
"args": [
"YOUR_ABSOLUTE_PATH/server.py"
]
}
}
}
Note: You may need to use the absolute path to your Python executable instead of just "python" if Claude has trouble finding it.
Example Tool Usage
Input arguments from Claude:
{
"path": "./sample_folder",
"recursive": true
}
Output returned to Claude (JSON string):
{
"path": "C:\\path\\to\\sample_folder",
"total_files": 2,
"total_folders": 1,
"files": [
"data.txt",
"image.png"
],
"folders": [
"subfolder"
],
"recursive_total_files": 5,
"recursive_total_folders": 3
}
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.