AI & Machine Learning
isgenai.com
Checks text, web pages, and images for AI-use disclosures and C2PA Content Credentials, and extracts saved generation prompts and settings.
ENDPOINT 1
https://isgenai.com/mcp
MCP server metadata
- Name
- isgenai
- Version
- 1.0.2
isGenAI (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: - check_text: text or code (up to 16,000 characters). Finds statements of AI use and named AI tools, quoting the sentence. It does not judge authorship from writing style. - check_url: a public web page or file URL. Reads AI labels, disclosures and file records on that page or file. - check_image: an image by public URL or base64 (up to 20 MiB). Reads C2PA, AI labels, saved settings and metadata; a detector estimate, when shown, is labelled LIKELY AI and is not proof. - extract_saved_prompt: 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. - read_content_credentials: reads a C2PA manifest and reports cryptographic validation and signer trust as separate findings. What results prove and do not prove: findings come from records in the supplied copy, not from guessing at pixels. A record shows what the file or page states; records can be edited or removed. NO AI SIGNAL DETECTED does not mean a person made the content: screenshots, re-exports and social uploads often strip records, so ask for the original file when it matters. isGenAI does not verify whether depicted events are true and gives no legal advice. When you answer, state the headline and the specific evidence with its source, repeat the main caveat, and cite methodology_url. Pass public URLs instead of base64 when you can.
Known tools 5
check_textCheck pasted text or code (up to 16,000 characters) for statements of AI use and named AI tools such as ChatGPT, Claude, Gemini or Copilot, quoting the exact sentence.
Inferred read-onlycheck_urlFetch a public web page or file and read AI labels, AI-use statements, Content Credentials and saved creation records found there.
Inferred read-onlycheck_imageCheck an image (PNG, JPEG, WebP, AVIF or single-page TIFF, up to 20 MiB) by public URL or base64 for C2PA Content Credentials, AI labels, saved generation settings and metadata.
Inferred read-onlyextract_saved_promptRead the prompt, negative prompt, model and settings saved inside an image by AUTOMATIC1111, ComfyUI (including Flux workflows), InvokeAI or NovelAI.
Inferred read-onlyread_content_credentialsRead C2PA Content Credentials from an image, video, audio or PDF file (by public URL or base64, up to 20 MiB).
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.isgenai]
url = "https://isgenai.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"isgenai": {
"type": "http",
"url": "https://isgenai.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: isgenai
Remote MCP URL: https://isgenai.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"isgenai": {
"url": "https://isgenai.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"isgenai": {
"type": "http",
"url": "https://isgenai.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "isgenai",
"transport": "streamable-http",
"url": "https://isgenai.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.