# net.identifai/mcp Detect AI-generated images, videos, and audio with identifAI's deepfake detection tools. - **Type:** MCP server - **Trust:** 30/100 (D), scored on the content rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 1.2.3 - **Author:** net.identifai - **License:** Unknown - **Endpoints:** streamable-http https://mcp.identifai.net - **Source:** https://mcp.identifai.net - **Endpoint health:** reachable (last checked 2026-10-01T02:06:50.486Z, 6 samples) — uptime is not a security property and is not part of the trust score - **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport) ## Trust 30/100 (D), scored on the content rubric - Publisher verified: no - Install scripts: suspicious script found - Prompt-injection scan: findings present - Obfuscation scan: clean - Evidence age: 32 days ## Security scan - **Status:** warnings - **Scanned:** 2026-09-03T21:20:38.456Z - **Version scanned:** live - **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it. **Findings** - injection-shaped content (warning) in the `classify_image` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `classify_image_url` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `get_image_classification` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `get_all_image_classifications` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `get_classification_heatmap` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `override_image_classification` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `classify_video` tool: Exfiltration-shaped instruction - injection-shaped content (warning) in the `classify_video_url` tool: Exfiltration-shaped instruction - …and 11 more (full list in the JSON view) ## Tools 19 declared. Observed from a live `tools/list` probe. - `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 identifi - `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 th - `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 unt - `get_all_image_classifications` — Retrieve classification results for multiple images in a single request. Accepts up to 100 identifiers. Useful for batch result polling. - `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 withHea - `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 feed - `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 whi - `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. - `get_video_classification` — Retrieve the classification result for a previously submitted video. Poll until the result is ready — video classification is always asynchronous. - `get_all_video_classifications` — Retrieve classification results for multiple videos in a single request. Accepts up to 100 identifiers. - `override_video_classification` — Manually override the classification verdict for a previously classified video. Sets the result to either "human" or "artificial". - `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 classif - `classify_audio_url` — Submit a publicly accessible audio URL for AI-generated speech detection. Returns a classification identifier for async result retrieval. Authentication: provid - `get_audio_classification` — Retrieve the classification result for a previously submitted audio file. Poll until the result is ready. - `get_all_audio_classifications` — Retrieve classification results for multiple audio files in a single request. Accepts up to 100 identifiers. - `override_audio_classification` — Manually override the classification verdict for a previously classified audio file. Sets the result to either "human" or "artificial". - `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 b - `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; resul - `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 ("auth ## Install **Verdict: do-not-install** — Do not install: 19 injection-shaped patterns found in this entry's own text — it may try to steer the model that loads it. **Blocking** - 19 injection-shaped patterns found in this entry's own text — it may try to steer the model that loads it. — tool:classify_image#apiKey: Exfiltration-shaped instruction · tool:classify_image_url#apiKey: Exfiltration-shaped instruction · tool:get_image_classification#apiKey: Exfiltration-shaped instruction **Cautions** (coverage gaps and advisories — never blocking) - No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it. - No publisher has proved control of this listing; it is indexed, not vouched for. **Client configuration withheld.** Client configs are withheld because this entry has a blocking finding. Show the warnings below to the person installing it. If they have seen the findings and still want to proceed, request the plan again with acknowledge_warnings=true. ## Blast radius Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface. - Floor 9, ceiling 27 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/net.identifai%2Fmcp - Install plan: https://forgeregistry.com/api/v1/packages/net.identifai%2Fmcp/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/net.identifai%2Fmcp - HTML page: https://forgeregistry.com/registry/net.identifai%2Fmcp - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.