playbooks
Learn Cursor Rules Windsurf Rules MCPs Modes
Log in

File Finder MCP server

Provides efficient file search and retrieval capabilities within a networked environment using TypeScript and Node.js, offering both standard and HTTP-based execution modes.
Back to servers
Setup instructions
Provider
Sergey
Release date
Feb 27, 2025
Language
TypeScript
View on GitHub

This MCP repository provides two servers: File Finder MCP for searching files and Whisper STT MCP for speech-to-text conversion. Both servers follow the Model Context Protocol (MCP) specification and can be integrated with tools like VS Code's Cline extension.

File Finder MCP Server

The File Finder MCP server allows searching for files containing specific text fragments in their names.

Prerequisites

  • Node.js (version 14 or higher)
  • npm (version 6 or higher)
  • Python 3.6 or higher (for HTTP server)

Installation

  1. Clone or download the repository
  2. Navigate to the project directory
  3. Install dependencies: 
    npm install
  4. Build the project: 
    npm run build

Running the Server

Option 1: Direct MCP Server Launch

Run the MCP server directly using Node.js:

npm start

or

node build/index.js

This will start the server, which will wait for JSON-RPC requests on stdin/stdout.

Option 2: HTTP Server and MCP Proxy

This option uses a Python HTTP server and an MCP proxy that forwards requests to the HTTP server:

  1. First, start the HTTP server:

    npm run start:python

    or

    python main.py

  2. Then, in another terminal, start the MCP proxy:

    npm run start:http

    or

    node build/index-http.js

Option 3: VS Code Integration (Cline Extension)

To integrate the server with VS Code and the Cline extension:

  1. Find the MCP settings file:

    • Windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
    • macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
    • Linux: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

  2. Add the following configuration to the mcpServers object in the settings file:

"file-finder-mcp": {
  "command": "node",
  "args": ["<FULL_PATH_TO_PROJECT>/build/index.js"],
  "disabled": false,
  "autoApprove": []
}

For using the HTTP proxy:

"file-finder-mcp-http": {
  "command": "node",
  "args": ["<FULL_PATH_TO_PROJECT>/build/index-http.js"],
  "disabled": false,
  "autoApprove": []
}

Replace <FULL_PATH_TO_PROJECT> with the actual path to your project directory.

  1. Restart VS Code to load the updated settings.

Available Tools

The MCP server provides one tool:

  • search_files: Searches for files containing the specified fragment in their names
    • Parameters:
      • fragment (string, required): Text fragment to search for in file names

Usage Example

<use_mcp_tool>
<server_name>file-finder-mcp</server_name>
<tool_name>search_files</tool_name>
<arguments>
{
  "fragment": ".py"
}
</arguments>
</use_mcp_tool>

This example searches for all files containing ".py" in their names.

HTTP Server API

The HTTP server provides a REST API for searching files with the specified fragment in their names.

To search for files, send a GET request to /search with the query parameter q:

http://localhost:8080/search?q=.json

This request will return a JSON array with information about all files containing ".json" in their names.

Whisper STT MCP Server

The Whisper STT MCP server provides speech-to-text functionality using the faster-whisper library, converting audio data to text with automatic language detection.

Prerequisites

  • Node.js (version 14 or higher)
  • npm (version 6 or higher)
  • Python 3.6 or higher
  • faster-whisper (install with pip install faster-whisper)

Installation

  1. Clone or download the repository
  2. Navigate to the project directory
  3. Install dependencies: 
    npm install
pip install faster-whisper
  4. Build the project: 
    npm run build

Running the Server

Option 1: Direct MCP Server Launch

Run the MCP server directly using Node.js:

npm run start:whisper

or

node build/whisper-index.js

Option 2: HTTP Server and MCP Proxy

  1. First, start the HTTP server:

    npm run start:whisper:python

    or

    python whisper_server.py

  2. Then, in another terminal, start the MCP proxy:

    npm run start:whisper:http

    or

    node build/whisper-index-http.js

Option 3: VS Code Integration (Cline Extension)

Add the following configuration to the mcpServers object in the Cline MCP settings file:

"whisper-stt-mcp": {
  "command": "node",
  "args": ["<FULL_PATH_TO_PROJECT>/build/whisper-index.js"],
  "disabled": false,
  "autoApprove": []
}

For using the HTTP proxy:

"whisper-stt-mcp-http": {
  "command": "node",
  "args": ["<FULL_PATH_TO_PROJECT>/build/whisper-index-http.js"],
  "disabled": false,
  "autoApprove": []
}

Replace <FULL_PATH_TO_PROJECT> with the actual path to your project directory and restart VS Code.

Available Tools

The MCP server provides one tool:

  • transcribe_audio: Converts audio data to text using faster-whisper
    • Parameters:
      • audio_base64 (string, required): Audio data in base64 format
      • language (string, optional): Language code (e.g., "en", "ru"). If not specified, the language will be automatically detected.

Usage Example

<use_mcp_tool>
<server_name>whisper-stt-mcp</server_name>
<tool_name>transcribe_audio</tool_name>
<arguments>
{
  "audio_base64": "BASE64_ENCODED_AUDIO_DATA",
  "language": "ru"
}
</arguments>
</use_mcp_tool>

This example converts audio data to text, assuming the audio is in Russian.

HTTP Server API

The HTTP server runs on http://localhost:8081 and provides a REST API for transcribing audio data to text.

To transcribe audio, send a POST request to /transcribe with a JSON body containing:

  • audio: base64-encoded audio data
  • language (optional): language code (e.g., "en", "ru")

Troubleshooting

  • If you get a "No connection found for server" error, make sure you've restarted VS Code after updating the MCP settings.
  • If the server doesn't respond, check that the path in the MCP settings is correct and points to the built JavaScript file.
  • Make sure the server is properly built by running npm run build before attempting to use it.
  • For using the HTTP proxy, ensure that the corresponding HTTP server is running (on port 8080 for file-finder or 8081 for whisper-stt).
  • If you encounter issues with faster-whisper, make sure the library is properly installed and you have the necessary dependencies for GPU usage (if you're using GPU).

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "file-finder-mcp" '{"command":"node","args":["<\u041f\u041e\u041b\u041d\u042b\u0419_\u041f\u0423\u0422\u042c_\u041a_\u041f\u0420\u041e\u0415\u041a\u0422\u0423>/build/index.js"],"disabled":false,"autoApprove":[]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "file-finder-mcp": {
            "command": "node",
            "args": [
                "<\u041f\u041e\u041b\u041d\u042b\u0419_\u041f\u0423\u0422\u042c_\u041a_\u041f\u0420\u041e\u0415\u041a\u0422\u0423>/build/index.js"
            ],
            "disabled": false,
            "autoApprove": []
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "file-finder-mcp": {
            "command": "node",
            "args": [
                "<\u041f\u041e\u041b\u041d\u042b\u0419_\u041f\u0423\u0422\u042c_\u041a_\u041f\u0420\u041e\u0415\u041a\u0422\u0423>/build/index.js"
            ],
            "disabled": false,
            "autoApprove": []
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later