English Français العربية

isGenAI

Official registry Media and design

Free read-only checks for evidence of AI use in text, links, images, saved prompts and C2PA.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http isgenai 'https://isgenai.com/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "isgenai": {
            "type": "http",
            "url": "https://isgenai.com/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. isGenAI MCP server
  2. Tools (all read-only)
  3. Connect
  4. What results prove and do not prove
  5. Also available
  6. License

isGenAI MCP server

A free, hosted Model Context Protocol server that checks images, links, text and code for recorded evidence of AI use: C2PA Content Credentials, IPTC "AI-generated" labels, AI-use statements and the prompts saved by Stable Diffusion tools. Every finding quotes its source. It never gives a verdict from how pixels look.

This repository holds the listing metadata, client configuration and examples for the hosted service. The server itself runs at isgenai.com; there is nothing to install.

Tools (all read-only)

ToolWhat it does
check_textFinds statements of AI use and named AI tools (ChatGPT, Claude, Gemini, Copilot…) in text or code, quoting the sentence. It does not judge authorship from writing style.
check_urlFetches a public page or file and reads AI labels, AI-use statements, Content Credentials and saved creation records.
check_imageChecks an image (PNG, JPEG, WebP, AVIF, TIFF up to 20 MiB) by public URL or base64 for C2PA, AI labels, saved generation settings and metadata.
extract_saved_promptReads the prompt, negative prompt, model and settings saved by AUTOMATIC1111, ComfyUI, InvokeAI or NovelAI. Never invents a prompt.
read_content_credentialsReads a C2PA manifest and reports cryptographic validation and signer trust as separate findings.

MCP checks are private: no public report page is created.

Connect

Claude Code

claude mcp add --transport http isgenai https://isgenai.com/mcp

Claude Desktop, Cursor, Windsurf, VS Code and other clients (see examples/):

{
  "mcpServers": {
    "isgenai": { "type": "http", "url": "https://isgenai.com/mcp" }
  }
}

Raw request

curl -s https://isgenai.com/mcp \
  -H 'content-type: application/json' -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"check_image","arguments":{"url":"https://isgenai.com/examples/guide-lab/parameters-tEXt.png"}}}'

What results prove and do not prove

Findings come from records in the supplied copy. A record shows what the file or page states, and 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 check the original file when it matters.

Also available

License

The files in this repository are released under the MIT License. The hosted service is governed by the isGenAI terms and privacy policy.

Frequently asked questions

What is isGenAI?

Free read-only checks for evidence of AI use in text, links, images, saved prompts and C2PA.

How do I install isGenAI?

It runs as a remote server. In Claude Code: claude mcp add --transport http isgenai 'https://isgenai.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does isGenAI need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is isGenAI open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains isGenAI?

It is published by vagabond11. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.