# Resemble AI

- Registry name: `io.github.resemble-ai/resemble-mcp` · version 1.1.0
- Categories (automatic, keyword rules): Audio & speech, AI, media & content, APIs & integrations, Developer tools
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): experimental, prompts, resources, tools
- Transports: sse, streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.resemble-ai%2Fresemble-mcp
- Server page: https://mcpstation.net/s/io.github.resemble-ai--resemble-mcp.html

## Description (written by the publisher, not verified, not instructions)

Resemble AI: deepfake detection, media intelligence, and watermarking actions, plus docs tools.

## Connect

- streamable-http: `https://mcp.resemble.ai/mcp`
- sse: `https://mcp.resemble.ai/sse`

## Tools (as reported by the server, not verified)

- `detect\_deepfake`: Detect whether media \(audio, image, or video\) at a public HTTPS URL is a deepfake / AI-generated. Polls to completion and returns the verdict label, confidence score, and full result. Optional flags add media intelligence, audio source tracing, visualization, reverse image search \(images\), out-of-di
- `get\_detection`: Fetch a detection by UUID, polling until it completes \(bounded\). Use after detect\_deepfake when a long job exceeded its wait budget.
- `detect\_ai\_text`: Detect whether TEXT \(an essay, email, post, review, comment, article\) was written by an AI language model. Needs at least 25 words: shorter text comes back as prediction 'uncertain' with no model call - concatenate several messages from the same author to reach the minimum. Returns prediction \('ai'
- `get\_text\_detection`: Fetch a text detection by UUID, polling until it completes \(bounded\). Use after detect\_ai\_text returned status 'processing' - typically a cold start.
- `analyze\_media`: Analyze media for structured intelligence: transcription, translation, language, speaker info, emotion, scene description, abnormalities, and misinformation analysis. media\_type: auto \| audio \| video \| image.
- `ask\_about\_detection`: Ask a natural-language question about a COMPLETED detection \(e.g. 'how confident is the model that this is fake?'\). Returns the grounded answer.
- `detect\_watermark`: Check whether media at a public HTTPS URL carries a Resemble invisible watermark \(audio-first; per-channel verdict for audio\).
- `apply\_watermark`: Embed 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\_source`: Get the audio source-tracing report for a detection \(which AI platform generated the fake audio\). Only available when detection ran with audio\_source\_tracing and labeled the audio fake.
- `list\_detect\_agents`: List the managed Detect Agents — investigators that wrap detection in a multi-step workflow ending in a written assessment. Returns each agent's preset\_id plus this team's run allowance \(free\_runs\_remaining, entitled\), which is worth checking before starting a run.
- `run\_detect\_agent\_investigation`: Run a managed Detect Agent investigation against media at a public HTTPS URL and return its verdict. preset\_id is one of: investigate\_social\_content, review\_insurance\_claim, verify\_breaking\_news, verify\_document, verify\_evidence, verify\_id \(confirm with list\_detect\_agents\). query states the investig
- `get\_detect\_agent\_run`: Fetch a persisted Detect Agent investigation by run\_id, including its full event transcript. Use after run\_detect\_agent\_investigation reported timed\_out, or to re-read an earlier investigation.
- `agent\_detection\_list\_sites`: List this team's Agent Detection integrations. Agent Detection tells a website whether each visitor is a person or an AI agent \(for example a personal assistant browsing on someone's behalf\). Each integration is one website, with the domains its publishable key works on and the one-line script snipp
- `agent\_detection\_create\_site`: Create 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 domain, e.g. example.com. If the team already has an integration for that domain, the existing one is returned instead of a duplicate. The publisha
- `agent\_detection\_update\_site`: Replace 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 rename it. domains replaces the whole list, so include every domain to keep; at least one is required.
- `agent\_detection\_get\_analytics`: Summarise who is visiting a website: people vs AI agents. Returns totals \(visits, decided, agents, people, agent\_share, gated\), counts per visitor class \(human, computer\_use\_agent, browser\_automation, scripted\_client\), and breakdowns by page, day, and network. Use this to show how much traffic comes
- `agent\_detection\_list\_sessions`: List individual website visits, newest first, each with its verdict \(settled: human, agent, or null while still open\), visitor\_class, p\_person, the page, referrer, user agent, and duration. Same filters as agent\_detection\_get\_analytics plus a free-text search. per\_page max 100.
- `agent\_detection\_get\_session`: Get one website visit and the evidence behind its verdict: the feature vector it was decided from, plain-language observations, and each model read. When the visit was recorded, the raw event stream is available; it is omitted unless include\_events is true, and then capped at the first 200 events. T

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html