Servidor MCP
Resemble AI
io.github.resemble-ai/resemble-mcp
Qué hace este MCP
Analyzes media and text for deepfakes, AI authorship, misinformation, provenance watermarks, audio sources, and website human-versus-agent traffic.
Capacidades
Herramientas
18
herramientas
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 publishable key is safe to put in a public web page: it only sends
telemetry, only from the listed domains. Never put the Resemble API key in
a page. Paste the snippet into the <head> of every page to cover; the page
can then listen for the 'resemble:verdict' event or call ResembleAgentDetection.onVerdict().
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_create_siteArguments', 'required': ['domain'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'default': ''}, 'domain': {'type': 'string', 'title': 'Domain'}}}
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 from agents and which pages they use, so the site can be made easier
for helpful agents and protected from harmful ones.
Filters are optional: site_id (one integration), settled ('human' or
'agent'), page_path, and since/until as ISO 8601 times. agent_share is
agents / decided visits, or null when nothing is decided yet.
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_get_analyticsArguments', 'properties': {'since': {'type': 'string', 'title': 'Since', 'default': ''}, 'until': {'type': 'string', 'title': 'Until', 'default': ''}, 'settled': {'type': 'string', 'title': 'Settled', 'default': ''}, 'site_id': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Site Id', 'default': None}, 'page_path': {'type': 'string', 'title': 'Page Path', 'default': ''}}}
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. The verdict is advisory: it comes from browser signals, which
a determined attacker can fake.
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_get_sessionArguments', 'required': ['session_id'], 'properties': {'session_id': {'type': 'integer', 'title': 'Session Id'}, 'include_events': {'type': 'boolean', 'title': 'Include Events', 'default': False}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_list_sessionsArguments', 'properties': {'page': {'type': 'integer', 'title': 'Page', 'default': 1}, 'since': {'type': 'string', 'title': 'Since', 'default': ''}, 'until': {'type': 'string', 'title': 'Until', 'default': ''}, 'search': {'type': 'string', 'title': 'Search', 'default': ''}, 'settled': {'type': 'string', 'title': 'Settled', 'default': ''}, 'site_id': {'anyOf': [{'type': 'integer'}, {'type': 'null'}], 'title': 'Site Id', 'default': None}, 'per_page': {'type': 'integer', 'title': 'Per Page', 'default': 25}, 'page_path': {'type': 'string', 'title': 'Page Path', 'default': ''}}}
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 snippet to paste into the site's <head>.
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_list_sitesArguments', 'properties': {}}
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.
Esquema de entrada
{'type': 'object', 'title': 'agent_detection_update_siteArguments', 'required': ['site_id', 'domains'], 'properties': {'name': {'type': 'string', 'title': 'Name', 'default': ''}, 'domains': {'type': 'array', 'items': {'type': 'string'}, 'title': 'Domains'}, 'site_id': {'type': 'integer', 'title': 'Site Id'}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'analyze_mediaArguments', 'required': ['url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'media_type': {'type': 'string', 'title': 'Media Type', 'default': 'auto'}, 'structured_json': {'type': 'boolean', 'title': 'Structured Json', 'default': True}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 120}}}
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).
Esquema de entrada
{'type': 'object', 'title': 'apply_watermarkArguments', 'required': ['url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'strength': {'type': 'number', 'title': 'Strength', 'default': 0.2}, 'custom_message': {'type': 'string', 'title': 'Custom Message', 'default': ''}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 120}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'ask_about_detectionArguments', 'required': ['detect_uuid', 'query'], 'properties': {'query': {'type': 'string', 'title': 'Query'}, 'detect_uuid': {'type': 'string', 'title': 'Detect Uuid'}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 120}}}
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' | 'human'), confidence (how sure the model is of that prediction; it
is NOT an AI probability, so 'human' at 0.95 means strongly human), and the
full result. Only the first ~400 words are read; chunk longer documents.
A result can take several minutes when the model is cold or jobs are
queued - if status is still 'processing' when the wait budget ends, resume
with get_text_detection(uuid). Detection is probabilistic, not proof of authorship.
Esquema de entrada
{'type': 'object', 'title': 'detect_ai_textArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text'}, 'threshold': {'type': 'number', 'title': 'Threshold', 'default': 0.5}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 240}, 'zero_retention_mode': {'type': 'boolean', 'title': 'Zero Retention Mode', 'default': False}}}
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-distribution detection, and zero-retention (auto-delete media after
analysis). model_type: auto | image | talking_head.
Esquema de entrada
{'type': 'object', 'title': 'detect_deepfakeArguments', 'required': ['url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'visualize': {'type': 'boolean', 'title': 'Visualize', 'default': False}, 'model_type': {'type': 'string', 'title': 'Model Type', 'default': 'auto'}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 120}, 'run_intelligence': {'type': 'boolean', 'title': 'Run Intelligence', 'default': False}, 'use_ood_detector': {'type': 'boolean', 'title': 'Use Ood Detector', 'default': False}, 'use_reverse_search': {'type': 'boolean', 'title': 'Use Reverse Search', 'default': False}, 'zero_retention_mode': {'type': 'boolean', 'title': 'Zero Retention Mode', 'default': False}, 'audio_source_tracing': {'type': 'boolean', 'title': 'Audio Source Tracing', 'default': False}}}
detect_watermark
Check whether media at a public HTTPS URL carries a Resemble invisible
watermark (audio-first; per-channel verdict for audio).
Esquema de entrada
{'type': 'object', 'title': 'detect_watermarkArguments', 'required': ['url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'get_detect_agent_runArguments', 'required': ['preset_id', 'run_id'], 'properties': {'run_id': {'type': 'string', 'title': 'Run Id'}, 'preset_id': {'type': 'string', 'title': 'Preset Id'}}}
get_detection
Fetch a detection by UUID, polling until it completes (bounded). Use after
detect_deepfake when a long job exceeded its wait budget.
Esquema de entrada
{'type': 'object', 'title': 'get_detectionArguments', 'required': ['uuid'], 'properties': {'uuid': {'type': 'string', 'title': 'Uuid'}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 60}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'get_text_detectionArguments', 'required': ['uuid'], 'properties': {'uuid': {'type': 'string', 'title': 'Uuid'}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 240}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'list_detect_agentsArguments', 'properties': {}}
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 investigation objective; check_urls adds URLs for the agent to check.
Consumes a run of the team's allowance. `label`/`score` are the Detect
evidence and are the only basis for an authenticity claim; `verdict` is the
agent's written assessment. If timed_out is true the investigation is still
running server-side — retrieve it later with get_detect_agent_run.
Esquema de entrada
{'type': 'object', 'title': 'run_detect_agent_investigationArguments', 'required': ['preset_id', 'url'], 'properties': {'url': {'type': 'string', 'title': 'Url'}, 'query': {'type': 'string', 'title': 'Query', 'default': ''}, 'preset_id': {'type': 'string', 'title': 'Preset Id'}, 'check_urls': {'type': 'string', 'title': 'Check Urls', 'default': ''}, 'max_wait_seconds': {'type': 'integer', 'title': 'Max Wait Seconds', 'default': 180}}}
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.
Esquema de entrada
{'type': 'object', 'title': 'trace_audio_sourceArguments', 'required': ['uuid'], 'properties': {'uuid': {'type': 'string', 'title': 'Uuid'}}}
Historial
Cambios recientes en herramientas
Añadido
agent_detection_get_session
25 de September de 2026 a las 02:55
Añadido
agent_detection_list_sessions
25 de September de 2026 a las 02:55
Añadido
agent_detection_get_analytics
25 de September de 2026 a las 02:55
Añadido
agent_detection_update_site
25 de September de 2026 a las 02:55
Añadido
agent_detection_create_site
25 de September de 2026 a las 02:55
Añadido
agent_detection_list_sites
25 de September de 2026 a las 02:55
Añadido
get_detect_agent_run
25 de September de 2026 a las 02:55
Añadido
run_detect_agent_investigation
25 de September de 2026 a las 02:55
Añadido
list_detect_agents
25 de September de 2026 a las 02:55
Añadido
get_text_detection
25 de September de 2026 a las 02:55
Añadido
detect_ai_text
25 de September de 2026 a las 02:55
Añadido
trace_audio_source
17 de September de 2026 a las 12:49
Añadido
apply_watermark
17 de September de 2026 a las 12:49
Añadido
detect_watermark
17 de September de 2026 a las 12:49
Añadido
ask_about_detection
17 de September de 2026 a las 12:49
Añadido
analyze_media
17 de September de 2026 a las 12:49
Añadido
get_detection
17 de September de 2026 a las 12:49
Añadido
detect_deepfake
17 de September de 2026 a las 12:49
Descubrir
Servidores MCP similares
identifAI MCP Server
net.identifai/mcp
Detects AI-generated or manipulated images, videos, audio, and ticket documents, with asynchronous results, heatmaps, and manual …
Cybersecurity News & Breach Alerts — buy per-query in-session (bleepingwatch)
com.a2awire/data-cybersecurity-news-breach-alert
Provides query access to cybersecurity news and breach reporting, including hacks, ransomware, vulnerabilities, and patches.
ProofX - Content Protection for Creators
io.github.razashariff/proofx
Hashes, cryptographically protects, and verifies digital text content and creator ownership records.
unmarking
ing.unmark/unmarking
Inspects C2PA content credentials in media files and removes them while preserving the underlying media.
Automatic Image/Video Face Detection, Blur/Redaction & De-identification MCP — NoonAI DIS
com.dyndns-server.noon-ai/image-video-anonymization-mcp
Processes images and video to detect faces and perform blur, redaction, and de-identification.
Automatic Privacy Object Anonymize & Face Masking MCP — NoonAI DIS
com.dyndns-server.noon-ai/privacy-object-anonymize-mcp
Anonymizes privacy-sensitive objects and faces in media through masking and de-identification.
Automatic Image/Video Face Detection, Blur/Redaction & De-identification MCP — NoonAI DIS
com.dyndns-server.noon-ai/video-anonymization-mcp
Provides image and video face detection, blur, redaction, and privacy de-identification.
AI Metadata Cleaner
com.aimetadatacleaner/metadata-cleaner
Removes GPS, device, date, and AI-related metadata from videos, PDFs, RAW files, and photos.