Synphony

FastMCP server for Synphony video dataset management with Hugging Face Hub integration

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "rukasuamarike-synphony-mcp": {
      "command": "python",
      "args": [
        "/absolute/path/to/synphony-mcp/server.py"
      ],
      "env": {
        "HF_TOKEN": "hf_abcdefghijklmnopqrstuvwxyz12345",
        "SYNPHONY_ROOT_DIR": "/path/to/your/video/directory",
        "HF_DATASET_REPO_ID": "username/my-dataset"
      }
    }
  }
}

Synphony MCP is a Python-based server that helps you manage video datasets and publish them to Hugging Face Hub. It exposes a simple set of CLI-driven MCP connections and tooling to upload videos, list content, and verify configuration, all while keeping credentials secure through environment variables.

How to use

You run Synphony MCP as a local or integrated MCP server and connect to it from your MCP client. Start the server, then use the available tools to list videos, validate your setup, and upload your local videos to a Hugging Face Datasets repository.

How to install

Prerequisites: Python 3.8+ and a working Python environment.

# 1. Clone the project
git clone https://github.com/rukasuamarike/synphony-mcp.git
cd synphony-mcp

# 2. Install dependencies
pip install -r requirements.txt

# 3. Create and configure environment variables
cp .env.example .env
# Edit .env to set SYNPHONY_ROOT_DIR, HF_TOKEN, and HF_DATASET_REPO_ID as needed

Additional configuration and run notes

Configure how the MCP server runs in your environment. You can set up a Claude Desktop integration to start the server through a desktop MCP configuration that points to the Python runtime and the server script, with the root directory for videos supplied as an environment variable.

{
  "mcpServers": {
    "synphony-mcp": {
      "command": "python",
      "args": ["/absolute/path/to/synphony-mcp/server.py"],
      "env": {
        "SYNPHONY_ROOT_DIR": "/path/to/your/video/directory"
      }
    }
  }
}

Security and future improvements

Never expose tokens in code or logs. Use environment variables for sensitive credentials and validate paths to prevent directory traversal. You can extend the server with additional MCP tools for Hub uploads, manifest generation, or per-file metadata.

Available tools

list_videos

List video files in a directory managed by the server.

get_server_info

Retrieve current server configuration and status to verify reachability and health.

validate_setup

Check that the server environment and configuration are valid for operation.

upload_to_hf_datasets

Upload selected local video files to a Hugging Face Datasets repository using the Hub API. Returns per-file status and errors if any.