identifAI is an MCP server with 19 tools an agent can call, among them classify_audio, classify_audio_url, classify_image. It answers at https://mcp.identifai.net over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 12 September 2026; the last check, on 24 October 2026, succeeded.
Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
classify_audio | Upload an audio or speech file to detect whether it is human-recorded or AI-synthesized. Provide the audio content as a base64-encoded string. Returns a classification identifier for async result retrieval. WARNING: base64 encoding adds ~33 Inputs: apiKey, fileData, filename, refId, noCache, preventC2paForces |
classify_audio_url | Submit a publicly accessible audio URL for AI-generated speech detection. Returns a classification identifier for async result retrieval. Authentication: provide your Identifai API key via the apiKey parameter or configure the X-Api-Key HTT Inputs: apiKey, audioUrl, refId, noCache, preventC2paForces |
classify_image | Upload an image file to detect whether it is human-made or AI-generated. Provide the image content as a base64-encoded string. Returns a classification identifier for async result retrieval. WARNING: base64 encoding adds ~33% overhead to th Inputs: apiKey, fileData, filename, refId, withMorphing, withTampering |
classify_image_url | Submit a publicly accessible image URL to detect whether it is human-made or AI-generated. Returns a classification identifier for result retrieval. Supports the same analysis options as file-based classification. Authentication: provide yo Inputs: apiKey, imageUrl, refId, withMorphing, withTampering, withHeatmap |
classify_video | Upload a video file to detect whether it is human-made or AI-generated. Provide the video content as a base64-encoded string. The video is split into frames which are individually classified. Returns a classification identifier for async re Inputs: apiKey, fileData, filename, refId, frames, keyFrames |
classify_video_url | Submit a publicly accessible video URL for AI-generated content detection. Supports the same frame extraction and analysis options as file-based classification. Authentication: provide your Identifai API key via the apiKey parameter or conf Inputs: apiKey, videoUrl, refId, frames, keyFrames, keyFramesMethod |
get_all_audio_classifications | Retrieve classification results for multiple audio files in a single request. Accepts up to 100 identifiers. Inputs: apiKey, identifiers |
get_all_image_classifications | Retrieve classification results for multiple images in a single request. Accepts up to 100 identifiers. Useful for batch result polling. Inputs: apiKey, identifiers |
get_all_video_classifications | Retrieve classification results for multiple videos in a single request. Accepts up to 100 identifiers. Inputs: apiKey, identifiers |
get_audio_classification | Retrieve the classification result for a previously submitted audio file. Poll until the result is ready. Inputs: apiKey, identifier |
get_classification_heatmap | Retrieve a visual heatmap highlighting which regions of the image were detected as AI-generated. Requires the classification to have been submitted with withHeatmap enabled. Inputs: apiKey, identifier |
get_image_classification | Retrieve the classification result for a previously submitted image. Use the identifier returned by classify_image or classify_image_url. Poll this endpoint until the result is available. Inputs: apiKey, identifier |
get_tampering_batch_results | Retrieve the tampering detection results for a previously submitted batch of tickets. Poll until the "done" field is true. Each result contains a verdict ("authentic" or "tampered") and per-heuristic verdicts. Inputs: apiKey, batchId |
get_user_credits | Retrieve the current available and used classification credits for the authenticated Identifai account. Use this to check quota status before submitting large batches. Inputs: apiKey |
get_video_classification | Retrieve the classification result for a previously submitted video. Poll until the result is ready — video classification is always asynchronous. Inputs: apiKey, identifier |
override_audio_classification | Manually override the classification verdict for a previously classified audio file. Sets the result to either "human" or "artificial". Inputs: apiKey, identifier, classification |
override_image_classification | Manually override the classification verdict for a previously classified image. Sets the result to either "human" or "artificial". Used for corrections and feedback. Inputs: apiKey, identifier, classification |
override_video_classification | Manually override the classification verdict for a previously classified video. Sets the result to either "human" or "artificial". Inputs: apiKey, identifier, classification |
submit_tampering_tickets | Submit one or more ticket images (as base64-encoded strings) to the Identifai v2 API for batch tampering detection. Each ticket is analysed independently; results are retrieved asynchronously via get_tampering_batch_results using the return Inputs: apiKey, tickets, filenames, refIds, models |
Every block below points at https://mcp.identifai.net. Pick your client and copy.
claude mcp add --transport http identifai https://mcp.identifai.net
{
"mcpServers": {
"identifai": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.identifai.net"]
}
}
}{
"mcpServers": {
"identifai": {
"url": "https://mcp.identifai.net"
}
}
}{
"servers": {
"identifai": {
"type": "http",
"url": "https://mcp.identifai.net"
}
}
}{
"context_servers": {
"identifai": {
"url": "https://mcp.identifai.net"
}
}
}{
"mcpServers": {
"identifai": {
"serverUrl": "https://mcp.identifai.net"
}
}
}{
"mcpServers": {
"identifai": {
"url": "https://mcp.identifai.net"
}
}
}name: identifAI
version: 0.0.1
schema: v1
mcpServers:
- name: identifAI
type: streamable-http
url: https://mcp.identifai.net{
"mcpServers": {
"identifai": {
"httpUrl": "https://mcp.identifai.net"
}
}
}{
"mcpServers": {
"identifai": {
"type": "http",
"url": "https://mcp.identifai.net"
}
}
}{
"mcpServers": {
"identifai": {
"url": "https://mcp.identifai.net"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.identifai.net&type=streamable_http&id=identifai&name=identifAI
It answered our last check on 24 October 2026 in 143 ms. Over 6 checks since 12 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by identifai.net and served from mcp.identifai.net, the vendor's own domain: https://mcp.identifai.net.
19, as returned by the server's own tools/list on 22 September 2026: classify_audio, classify_audio_url, classify_image, classify_image_url, classify_video, classify_video_url, get_all_audio_classifications, get_all_image_classifications, and 11 more.
It answered our last check on 24 October 2026 in 143 ms. Over 6 checks since 12 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.identifai.net. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: net.identifai. Endpoint host: mcp.identifai.net. ARD identifier: urn:air:net.identifai:mcp:mcp.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.