What it does
The server checks images, videos and audio for deepfake manipulation artifacts, drawing on metadata, provenance chains and synthesis indicators. It exposes tools named detect_deepfake, analyze_audio_authenticity and check_image_provenance.
An assistant would use it when a user needs to examine whether a media file may have been synthetically generated or altered, such as checking the provenance of an image or the authenticity of an audio clip. Requests are made in natural language, with the relevant tool named in the prompt.
The server can be installed as a Python package and started from the command line over stdio transport, or added to an MCP client configuration such as Claude Desktop's.
Limitations and requirements
Requires an MCP-compatible client, such as Claude Desktop, configured to launch the server. The server communicates over stdio transport.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSOAI-ORG/deepfake-detector-mcp
Deepfake Detector MCP Server by MEOK AI Labs
v1.0.15As shown on registry.modelcontextprotocol.io when we last read it