Resemble AI MCP: deepfake and AI-text detection in your AI app

Add Resemble AI detection to Claude, ChatGPT or Cursor

1. 1Click Connect Resemble AI free. There's no sign-in, so its tools are ready at once.
2. 2Detection tools such as `detect_deepfake` and `detect_ai_text` only check content. `apply_watermark` changes media, and `agent_detection_create_site` and `agent_detection_update_site` change your Agent Detection setup, so switch those off if your AI app should only check.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Give your AI app a public link to an audio clip and ask whether it's a deepfake, then open Activity to see the `detect_deepfake` call.

Checks Resemble AI can run for you

• Check whether audio, an image or a video at a public HTTPS URL is a deepfake with `detect_deepfake`.
• Test whether an essay, email or review was written by an AI model with `detect_ai_text`; it needs at least 25 words.
• Check media for a Resemble invisible watermark with `detect_watermark`, or embed one with `apply_watermark`.
• See how many of a website's visitors are people and how many are AI agents with `agent_detection_get_analytics`.

Resemble AI's server has 18 tools; these are a few. The rest, including Detect Agent investigations and audio source tracing, appear when you add the connection.

Keep Resemble AI's changes in check

• Switch off `apply_watermark` and the Agent Detection site tools, and your AI app can still run detections.
• Use a policy to warn or block before your AI app creates or changes an Agent Detection site.
• Activity records every detection, so you can show what was checked and when.

What you get with Resemble AI and ContextGate

• Your AI apps can use Resemble AIClaude, Cursor, ChatGPT and other AI apps reach Resemble AI through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Resemble AI tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Resemble AI tools

Examples of what your AI apps can do in Resemble AI. You'll see the exact list of tools after you connect it.

• detect_deepfakeDetect whether media (audio, image, or video) at a public HTTPS URL is a deepfake / AI-generated. Polls to completion and returns the verdict label, con
• get_detectionFetch a detection by UUID, polling until it completes (bounded). Use after detect_deepfake when a long job exceeded its wait budget.
• detect_ai_textDetect whether TEXT (an essay, email, post, review, comment, article) was written by an AI language model. Needs at least 25 words: shorter text comes b
• get_text_detectionFetch a text detection by UUID, polling until it completes (bounded). Use after detect_ai_text returned status 'processing' - typically a cold start.
• analyze_mediaAnalyze media for structured intelligence: transcription, translation, language, speaker info, emotion, scene description, abnormalities, and misinforma
• ask_about_detectionAsk a natural-language question about a COMPLETED detection (e.g. 'how confident is the model that this is fake?'). Returns the grounded answer.
• detect_watermarkCheck whether media at a public HTTPS URL carries a Resemble invisible watermark (audio-first; per-channel verdict for audio).
• apply_watermarkEmbed an invisible Resemble provenance watermark into media (audio-first) and return the watermarked media URL. strength 0.0-1.0 (image/video only).
• trace_audio_sourceGet the audio source-tracing report for a detection (which AI platform generated the fake audio). Only available when detection ran with audio_source_tr
• list_detect_agentsList the managed Detect Agents — investigators that wrap detection in a multi-step workflow ending in a written assessment. Returns each agent's preset_
• run_detect_agent_investigationRun a managed Detect Agent investigation against media at a public HTTPS URL and return its verdict. preset_id is one of: investigate_social_content, re
• get_detect_agent_runFetch a persisted Detect Agent investigation by run_id, including its full event transcript. Use after run_detect_agent_investigation reported timed_out
• agent_detection_list_sitesList this team's Agent Detection integrations. Agent Detection tells a website whether each visitor is a person or an AI agent (for example a personal a
• agent_detection_create_siteCreate an Agent Detection integration for a website and return its publishable key (pk_live_...) and the script snippet to install. domain is the site's
• agent_detection_update_siteReplace the list of domains an Agent Detection integration's publishable key is valid on (for example to add a staging or www host), and optionally rena
• agent_detection_get_analyticsSummarise who is visiting a website: people vs AI agents. Returns totals (visits, decided, agents, people, agent_share, gated), counts per visitor class
• agent_detection_list_sessionsList individual website visits, newest first, each with its verdict (settled: human, agent, or null while still open), visitor_class, p_person, the page
• agent_detection_get_sessionGet one website visit and the evidence behind its verdict: the feature vector it was decided from, plain-language observations, and each model read. Whe