
Check content for AI evidence
isGenAI reads the evidence of AI use that files and pages carry: C2PA Content Credentials, AI labels and AI-use statements, prompts and settings saved by AUTOMATIC1111, ComfyUI, InvokeAI and NovelAI, and EXIF, IPTC and XMP metadata. Five read-only tools: check_text (declared AI use and named AI tools in text or code), check_url (a public page or file), check_image (an image by URL or base64, up to 20 MiB), extract_saved_prompt (the saved prompt and settings, never a reconstruction) and read_content_credentials (C2PA manifest, with cryptographic validation and signer trust reported separately).
Example path ·
https://isgenai.com/mcpIsGenAI (https://isgenai.com) is a free checker that reads evidence of AI use stored in files and pages: C2PA Content Credentials, AI labels and AI-use statements, saved prompts and generation settings, EXIF/IPTC/XMP metadata, and matching copies in isGenAI records. Every finding names its source.
Tools:
: text or code (up to 16,000 characters). Finds statements of AI use and named AI tools, quoting the sentence. For 100+ characters it also returns an AI-likelihood estimate.
: a public web page or file URL. Reads AI labels, disclosures and file records on that page or file.
: an image by public URL or base64 (up to 20 MiB). Reads C2PA, AI labels, saved settings and metadata; it also returns an AI-likelihood score from the image detector.
: reads a prompt, negative prompt, model and settings saved in the file by AUTOMATIC1111, ComfyUI, InvokeAI or NovelAI. It never invents or reconstructs a prompt.
: reads a C2PA manifest and reports cryptographic validation and signer trust as separate findings.
: takes the replies under an X (Twitter) post (text, author details, timing) and estimates what share look AI-generated or bot-driven, with per-reply scores and the signals behind them. An estimate, not proof.
1 in the ChatGPT listing