mcpField
S
Songcheck   Ai Music Detector

Songcheck Ai Music Detector

Local
github.com/afghanfansmedia-aiMedia & Design1Updated 15w ago

About Songcheck Ai Music Detector

Songcheck MCP brings SongCheck AI-content detection to agents such as Claude, ChatGPT, and Gemini. It analyzes audio, images, and video, and can scan a music folder, returning a verdict with related probability, confidence, or provenance details.

Key features

  1. 01Detect AI-generated music in audio
  2. 02Assess AI content in images and video
  3. 03Scan an entire music folder
  4. 04Return verdict, probability, and confidence
  5. 05Identify credentials and generator hints

Use cases

  1. 01Check whether a track is AI-generated
  2. 02Inspect an image or video for AI content
  3. 03Audit a music folder in batch

MCP support

The MCP server exposes tools for audio detection, media detection, catalog scanning, and service health. Files are sent to the SongCheck API for analysis.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

SongCheck MCP — AI music & media detection inside any AI agent

Detect AI-generated music (and images/video) straight from Claude, ChatGPT, Gemini, Grok, or GitHub Copilot. Ask in plain language:

"Is this song AI-generated?" · "Analyze this file for AI content."

Powered by SongCheck (Khaled Media) — a self-hosted v9-ensemble detector. Free: https://khaledmedia.com/songcheck

Tools it exposes

  • detect_ai_music(file_path) — audio → verdict (LIKELY AI-GENERATED / UNCERTAIN / LIKELY HUMAN), AI probability %, confidence, provenance (Content Credentials / SynthID), generator hints.
  • detect_ai_media(file_path) — image or video → AI-detection assessment.
  • scan_catalog(folder_path) — audit an ENTIRE music folder, report which tracks are AI.
  • songcheck_health() — service status.

Install (2 steps)

pip install "mcp[cli]" requests

Then add it to your agent's MCP config:

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "songcheck": {
      "command": "python",
      "args": ["/absolute/path/to/songcheck_mcp.py"]
    }
  }
}

Restart the agent. Now ask: "Use SongCheck to tell me if ~/Downloads/track.mp3 is AI-generated."

Pricing

  • Free: 5 checks/day. After that you'll get a "subscribe" message.
  • Unlimited: subscribe at https://khaledmedia.com/songcheck — you receive an API key by email. Set it via SONGCHECK_KEY in the config env.
  • Batch / whole-catalog scans require a subscription key.

Notes

  • Point at a different backend with SONGCHECK_API (default https://agencrew.com/sc-api).
  • The detector is tuned for AI music; a bare synthetic-voice clip with no music may read low (AI-voice mode is on the roadmap).
  • Privacy: the file is sent to the SongCheck API for analysis and not retained beyond the detection log.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.