isGenAI
Free read-only checks for evidence of AI use in text, links, images, saved prompts and C2PA.
我該用這個嗎
品質與安全性
發現項目（6）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 check_text 中
- MEDIUMTool description contains URL to non-standard domain在 check_url 中
- MEDIUMTool description contains URL to non-standard domain在 check_image 中
- MEDIUMTool description contains URL to non-standard domain在 extract_saved_prompt 中
- MEDIUMTool description contains URL to non-standard domain在 read_content_credentials 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"checker": {
"url": "https://isgenai.com/mcp"
}
}
}遠端端點
https://isgenai.com/mcpstreamable-http它能做什麼
工具清單
工具（5）
🟢check_text(text, kind)
Check 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. Does not judge authorship from writing style. Private: no public report is created. Docs: https://isgenai.com/developers/mcp
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 16000,
"description": "The text or code to check."
},
"kind": {
"description": "Use code for source code. Defaults to text.",
"type": "string",
"enum": [
"text",
"code"
]
}
},
"required": [
"text"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢check_url(url)
Fetch a public web page or file and read AI labels, AI-use statements, Content Credentials and saved creation records found there. Logins, paywalls and CAPTCHAs are not bypassed. No public report is created. Docs: https://isgenai.com/developers/mcp
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Public http(s) URL. Private network and local addresses are refused."
}
},
"required": [
"url"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢check_image(url, image_base64, file_name)
Check 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. Evidence comes from records in the file, not a visual-only verdict. No public report is created. Docs: https://isgenai.com/developers/mcp
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Public http(s) URL. Private network and local addresses are refused."
},
"image_base64": {
"type": "string",
"minLength": 1,
"maxLength": 27962284,
"description": "File bytes as base64 or a data: URL, up to 20 MiB decoded. Prefer url when the file is public."
},
"file_name": {
"description": "Original file name, if known.",
"type": "string",
"maxLength": 200
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢extract_saved_prompt(url, image_base64)
Read the prompt, negative prompt, model and settings saved inside an image by AUTOMATIC1111, ComfyUI (including Flux workflows), InvokeAI or NovelAI. Only reads records stored in the file; it never reconstructs or guesses a prompt. Screenshots and re-uploads usually remove these records. Docs: https://isgenai.com/developers/mcp
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"description": "Direct public URL of the original image file.",
"type": "string",
"minLength": 1,
"maxLength": 2048
},
"image_base64": {
"type": "string",
"minLength": 1,
"maxLength": 27962284,
"description": "File bytes as base64 or a data: URL, up to 20 MiB decoded. Prefer url when the file is public."
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢read_content_credentials(url, file_base64, file_name, media_type)
Read C2PA Content Credentials from an image, video, audio or PDF file (by public URL or base64, up to 20 MiB). Reports the manifest, recorded actions and digital source type, with cryptographic validation and signer trust as separate findings. Docs: https://isgenai.com/developers/mcp
輸入結構描述
{
"type": "object",
"properties": {
"url": {
"type": "string",
"minLength": 1,
"maxLength": 2048,
"description": "Public http(s) URL. Private network and local addresses are refused."
},
"file_base64": {
"type": "string",
"minLength": 1,
"maxLength": 27962284,
"description": "File bytes as base64 or a data: URL, up to 20 MiB decoded. Prefer url when the file is public."
},
"file_name": {
"description": "Original file name, if known.",
"type": "string",
"maxLength": 200
},
"media_type": {
"description": "MIME type of the base64 file, for example image/jpeg.",
"type": "string",
"maxLength": 100
}
},
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據