net.identifai/mcp

MCPcommunautéen ligne
v1.2.3net.identifaiUnknownMis à jour il y a 5 mois

Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.

État de l’endpointen ligne
vérifié il y a 5 jours · 774 ms
100 % des dernières 6 vérifications ont atteint cet endpoint
Fonctionne dans
ClaudeCursorCopilotChatGPTGemini

Déduit des transports déclarés par cette annonce (streamable-http). Un client absent de cette liste n’est pas écarté pour autant — c’est simplement quelque chose que Forge ne peut pas confirmer.

Indexé automatiquement depuis des sources publiques. Pas encore vérifié par son développeur sur Forge.Revendiquer cette annonce →
il y a 5 moisDernière mise à jour
Paquet
Auteurnet.identifai
LicenceUnknown
Version1.2.3
Sourcemcp-registry
Statut de confiance
D
30/100Risque
✓Listé dans l’index Forge+10/10
—Identité de l’éditeur vérifiée+0/30
→ Éditeur : aucune référence de dépôt n’est enregistrée pour cette annonce, `forge publish` ne peut donc pas vérifier la propriété automatiquement. Utilisez « Revendiquer cette annonce » ci-dessus — Forge les examine à la main.
—Vérification de domaine+0/10
→ Actuellement indisponible pour ce type d’annonce — la vérification de domaine ne s’exécute aujourd’hui que pour les paquets adossés à npm, cette ligne ne peut donc pas encore être obtenue ici, quel que soit le contenu hébergé sur le domaine.
—Analyse d’injection de prompt · constats+0/30
→ Éditeur : retirez du code les instructions destinées aux clients d’IA plutôt qu’à des lecteurs humains
✓Analyse d’obfuscation / exfiltration · propre+20/20
StatutIndexé par la communauté
ÉditeurNon vérifié
SignatureNon signé
Domaine—
Provenance—
DépendancesNon audité
Surface d’outils19 outils · aucun privilégié
Analyse de sécurité⚠ Avertissements (19)vlive · il y a 1 moisQuelle est l’efficacité de cette analyse ?
PROMPTtool:classify_image#apiKeyExfiltration-shaped instruction
PROMPTtool:classify_image_url#apiKeyExfiltration-shaped instruction
PROMPTtool:get_image_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:get_all_image_classifications#apiKeyExfiltration-shaped instruction
PROMPTtool:get_classification_heatmap#apiKeyExfiltration-shaped instruction
PROMPTtool:override_image_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:classify_video#apiKeyExfiltration-shaped instruction
PROMPTtool:classify_video_url#apiKeyExfiltration-shaped instruction
PROMPTtool:get_video_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:get_all_video_classifications#apiKeyExfiltration-shaped instruction
PROMPTtool:override_video_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:classify_audio#apiKeyExfiltration-shaped instruction
PROMPTtool:classify_audio_url#apiKeyExfiltration-shaped instruction
PROMPTtool:get_audio_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:get_all_audio_classifications#apiKeyExfiltration-shaped instruction
PROMPTtool:override_audio_classification#apiKeyExfiltration-shaped instruction
PROMPTtool:get_user_credits#apiKeyExfiltration-shaped instruction
PROMPTtool:submit_tampering_tickets#apiKeyExfiltration-shaped instruction
PROMPTtool:get_tampering_batch_results#apiKeyExfiltration-shaped instruction
ÉvaluationsAucune
Indexé13 juin 2026

La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.

Outils

19 outils · aucun privilégié · 19 signalés pour injection
Observé en direct depuis l’endpoint du fournisseur1mo ago

Lu depuis un véritable échange MCP initialize → tools/list contre l’endpoint déclaré. Aucun outil n’a été invoqué — tools/list est l’appel d’introspection en lecture seule que le protocole prévoit pour cela. Cela reflète ce que le serveur annonçait à cet instant ; un endpoint hébergé n’est figé sur aucune version et peut changer sans préavis.

  • https://mcp.identifai.net19 outils · 956 ms
classify_imagerisque d’injectionUpload 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 the original file size. For images larger than 4 MB, use clas…

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 the original file size. For images larger than 4 MB, use clas…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
fileData*stringBase64-encoded raw binary content of the image file to classify. Do not pass a file-system path; encode the file bytes directly as base64. Only suitable for fi…
filenamestringOptional file name including extension (e.g. photo.jpg). Used to hint the media type.
refIdstringOptional caller-defined reference ID attached to the result
withMorphingbooleanEnable face morphing analysis on the image
withTamperingbooleanEnable tampering/splicing detection on the image
withHeatmapbooleanGenerate an AI content heatmap alongside the classification
noCachebooleanBypass cache and force a fresh classification
withNsfwbooleanEnable NSFW (Not Safe For Work) content detection on the image
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
classify_image_urlrisque d’injectionSubmit 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 your Identifai API key via the apiKey parameter or configure…

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 your Identifai API key via the apiKey parameter or configure…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
imageUrl*stringPublic HTTP/HTTPS URL of the image to classify
refIdstringOptional caller-defined reference ID
withMorphingbooleanEnable face morphing analysis
withTamperingbooleanEnable tampering/splicing detection
withHeatmapbooleanGenerate an AI content heatmap
noCachebooleanBypass cache and force fresh classification
withNsfwbooleanEnable NSFW (Not Safe For Work) content detection on the image
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
get_image_classificationrisque d’injectionRetrieve 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.

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.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier returned by the submission endpoint
get_all_image_classificationsrisque d’injectionRetrieve classification results for multiple images in a single request. Accepts up to 100 identifiers. Useful for batch result polling.

Retrieve classification results for multiple images in a single request. Accepts up to 100 identifiers. Useful for batch result polling.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifiers*arrayArray of classification identifiers (max 100)
get_classification_heatmaprisque d’injectionRetrieve a visual heatmap highlighting which regions of the image were detected as AI-generated. Requires the classification to have been submitted with withHeatmap enabled.

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.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier for which to fetch the heatmap
override_image_classificationrisque d’injectionManually override the classification verdict for a previously classified image. Sets the result to either "human" or "artificial". Used for corrections and feedback.

Manually override the classification verdict for a previously classified image. Sets the result to either "human" or "artificial". Used for corrections and feedback.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier to override
classification*stringThe correct classification value to apply
classify_videorisque d’injectionUpload 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 result retrieval. WARNING: base64 encoding adds ~33% overhead…

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 result retrieval. WARNING: base64 encoding adds ~33% overhead…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
fileData*stringBase64-encoded raw binary content of the video file to classify. Do not pass a file-system path; encode the file bytes directly as base64. Only suitable for fi…
filenamestringOptional file name including extension (e.g. clip.mp4). Used to hint the media type.
refIdstringOptional caller-defined reference ID
framesstringMaximum number of frames to extract and classify
keyFramesbooleanExtract key frames rather than uniform frames
keyFramesMethodstringAlgorithm used for key frame extraction
withTamperingbooleanEnable tampering detection on video frames
withMorphingbooleanEnable face morphing analysis on video frames
noCachebooleanBypass cache and force fresh classification
withNsfwbooleanEnable NSFW (Not Safe For Work) content detection on video frames
withAudioboolean[BETA] Analyze the audio track of the video in addition to the frames. Requires enablement in the pricing plan.
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
ensureFacePerFramebooleanEnsure at least one face is detected in each frame used for classification. Useful combined with withMorphing to detect face swaps. May increase processing tim…
classify_video_urlrisque d’injectionSubmit 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 configure the X-Api-Key HTTP header in your MCP client (recomme…

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 configure the X-Api-Key HTTP header in your MCP client (recomme…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
videoUrl*stringPublic HTTP/HTTPS URL of the video to classify
refIdstringOptional caller-defined reference ID
framesstringMaximum frames to extract
keyFramesbooleanExtract key frames
keyFramesMethodstringKey frame extraction algorithm
withTamperingbooleanEnable tampering detection
withMorphingbooleanEnable face morphing analysis
noCachebooleanBypass cache
withNsfwbooleanEnable NSFW (Not Safe For Work) content detection on video frames
withAudioboolean[BETA] Analyze the audio track of the video. Requires enablement in the pricing plan.
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
ensureFacePerFramebooleanEnsure at least one face is detected per frame. Useful with withMorphing.
get_video_classificationrisque d’injectionRetrieve the classification result for a previously submitted video. Poll until the result is ready — video classification is always asynchronous.

Retrieve the classification result for a previously submitted video. Poll until the result is ready — video classification is always asynchronous.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier returned by the submission endpoint
get_all_video_classificationsrisque d’injectionRetrieve classification results for multiple videos in a single request. Accepts up to 100 identifiers.

Retrieve classification results for multiple videos in a single request. Accepts up to 100 identifiers.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifiers*arrayArray of classification identifiers (max 100)
override_video_classificationrisque d’injectionManually override the classification verdict for a previously classified video. Sets the result to either "human" or "artificial".

Manually override the classification verdict for a previously classified video. Sets the result to either "human" or "artificial".

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier to override
classification*stringThe correct classification value to apply
classify_audiorisque d’injectionUpload 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% overhead to the original file size. For audio files large…

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% overhead to the original file size. For audio files large…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
fileData*stringBase64-encoded raw binary content of the audio file to classify. Do not pass a file-system path; encode the file bytes directly as base64. Only suitable for fi…
filenamestringOptional file name including extension (e.g. voice.mp3). Used to hint the media type.
refIdstringOptional caller-defined reference ID
noCachebooleanBypass cache and force fresh classification
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
classify_audio_urlrisque d’injectionSubmit 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 HTTP header in your MCP client (recommended).

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 HTTP header in your MCP client (recommended).

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
audioUrl*stringPublic HTTP/HTTPS URL of the audio to classify
refIdstringOptional caller-defined reference ID
noCachebooleanBypass cache
preventC2paForcesbooleanIf true, a C2PA signature will not force the classification to artificial
get_audio_classificationrisque d’injectionRetrieve the classification result for a previously submitted audio file. Poll until the result is ready.

Retrieve the classification result for a previously submitted audio file. Poll until the result is ready.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier returned by the submission endpoint
get_all_audio_classificationsrisque d’injectionRetrieve classification results for multiple audio files in a single request. Accepts up to 100 identifiers.

Retrieve classification results for multiple audio files in a single request. Accepts up to 100 identifiers.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifiers*arrayArray of classification identifiers (max 100)
override_audio_classificationrisque d’injectionManually override the classification verdict for a previously classified audio file. Sets the result to either "human" or "artificial".

Manually override the classification verdict for a previously classified audio file. Sets the result to either "human" or "artificial".

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
identifier*stringClassification identifier to override
classification*stringThe correct classification value to apply
get_user_creditsrisque d’injectionRetrieve the current available and used classification credits for the authenticated Identifai account. Use this to check quota status before submitting large batches.

Retrieve the current available and used classification credits for the authenticated Identifai account. Use this to check quota status before submitting large batches.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
submit_tampering_ticketsrisque d’injectionSubmit 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 returned batch_id. Supports PDF files (each page becomes a separa…

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 returned batch_id. Supports PDF files (each page becomes a separa…

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
tickets*arrayArray of base64-encoded raw binary content of ticket image/PDF files to analyse. Do not pass file-system paths; encode the file bytes directly as base64. Maxim…
filenamesarrayOptional array of filenames (e.g. ["ticket1.jpg", "ticket2.pdf"]). Must match the length of the tickets array if provided.
refIdsstringComma-separated list of reference IDs, one per ticket (e.g. "TICKET-001,TICKET-002"). Must match the number of tickets if provided.
modelsstringComma-separated list of model names to use for detection. If omitted, all models available in the pricing plan are used.
get_tampering_batch_resultsrisque d’injectionRetrieve 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.

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.

INJECTIONDans le paramètre apiKey : Exfiltration-shaped instructione MCP client is configured to send the X-Api-Key HTTP header (the rec…
ParamètreTypeDescription
apiKeystringIdentifai API key used to authenticate requests to the Identifai backend. Optional when the MCP client is configured to send the X-Api-Key HTTP header (the rec…
batchId*stringBatch identifier returned by submit_tampering_tickets

19 outils sur 19 ont publié une description.

Les noms et descriptions d’outils sont écrits par l’éditeur et affichés tels quels, comme du texte inerte. Ce sont les chaînes qu’un client MCP transmet à un modèle, alors Forge y recherche des motifs d’injection de prompt — tout constat apparaît avec l’analyse de sécurité ci-dessus. « Privilégié » est une correspondance de mot-clé sur le nom de l’outil, pas un audit de ce qu’il fait : un nom anodin peut tout de même tout faire.

À propos

Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools.

Mots-clés
mcp
Alternatives
Comparaison des surfaces d’outils…

Aucune couverture des dépendances

Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.