What it does
The server provides six tools. verify_text_origin checks whether a text was AI-generated, and detect_deepfake_image analyses an image URL for signs of AI generation. check_manipulation looks for signs of manipulation in a media URL. generate_content_certificate creates a verifiable certificate from a content hash, author and timestamp, and verify_certificate checks a certificate ID. provenance_chain traces the provenance of a content ID, with provenance chains described as C2PA-compliant.
It suits people who need to check whether text or images are AI-generated, confirm where content came from, or keep verifiable records of content. The readme also lists alignment with several EU AI Act articles (9, 13, 15, 26 and 50), with some marked as applicable only in certain cases.
It runs as an MCP server, and the readme gives setup steps for Claude Desktop, Cursor, VS Code and Windsurf. It is published under the MIT licence.
Limitations and requirements
The free tier is limited to 10 verifications per day. The Pro and Enterprise tiers are paid subscriptions, and the readme lists API access and custom models only under Enterprise. Some EU AI Act items are stated as applying only where applicable.
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/proofof-ai-mcp
Proofof Ai MCP Server by MEOK AI Labs
v1.0.9As shown on registry.modelcontextprotocol.io when we last read it