SongCheck MCP
Enables AI agents to detect AI-generated music, images, and video by analyzing files through SongCheck's ensemble detector, providing verdicts and confidence scores.
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_KEYin the configenv. - Batch / whole-catalog scans require a subscription key.
Notes
- Point at a different backend with
SONGCHECK_API(defaulthttps://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.
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.