Skip to content

Resemble AI MCP server

io.github.resemble-ai/resemble-mcpresemble-aistreamable-httpv1.4.0Scanned

Resemble AI: deepfake, AI-text, and site agent detection, Detect Agents, intelligence, watermarks.

18 tools: 8 change things and 10 only read.

Tools: 0 delete, 0 irreversible, 8 write, 10 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 5
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

8 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Resemble AI MCP server can do

The Resemble AI MCP server is published by the GitHub account resemble-ai. It has 18 tools. It can create or change data (8 tools: detect_deepfake, detect_ai_text, ask_about_detection, detect_watermark and 4 more), but cannot delete data. 10 tools only read.

4 tools bring in text other people can write (analyze_media, agent_detection_get_analytics, agent_detection_list_sessions and 1 more); 5 tools can send data out of your system (detect_deepfake, analyze_media, detect_watermark and 2 more).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 9, 2026, version 1.4.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

18 tools

Changes things 8Claude Code: ask
  • agent_detection_create_siteCreate an Agent Detection integration for a website and return its publishable key (pk_live_...) and the script snippet to install.No findings

    Why it is in this group

    • The name "agent_detection_create_site" says "create": a word for a change.
    Description, as the server wrote it
    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().
  • 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 rename it.No findings

    Why it is in this group

    • The name "agent_detection_update_site" says "update": a word for a change.
    Description, as the server wrote it
    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.
  • apply_watermarkEmbed an invisible Resemble provenance watermark into media (audio-first) and return the watermarked media URL.Can send data outNo findings

    Why it is in this group

    • The name "apply_watermark" says "apply": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Embed an invisible Resemble provenance watermark into media (audio-first) and return the watermarked media URL. strength 0.0-1.0 (image/video only).
  • ask_about_detectionAsk a natural-language question about a COMPLETED detection (e.g.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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_ai_textDetect whether TEXT (an essay, email, post, review, comment, article) was written by an AI language model.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.
  • detect_deepfakeDetect whether media (audio, image, or video) at a public HTTPS URL is a deepfake / AI-generated.Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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.
  • detect_watermarkCheck whether media at a public HTTPS URL carries a Resemble invisible watermark (audio-first; per-channel verdict for audio).Can send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    Check whether media at a public HTTPS URL carries a Resemble invisible watermark (audio-first; per-channel verdict for audio).
  • run_detect_agent_investigationRun a managed Detect Agent investigation against media at a public HTTPS URL and return its verdict.Can send data outNo findings

    Why it is in this group

    • The name "run_detect_agent_investigation" says "run": a word for a change.

    What it can reach

    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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.
Only reads 10Show 10 read-only tools
  • agent_detection_get_analyticsSummarise who is visiting a website: people vs AI agents.Reads text others writeNo findings

    Why it is in this group

    • The name "agent_detection_get_analytics" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "summarise" and "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    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.
  • 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.Reads text others writeNo findings

    Why it is in this group

    • The name "agent_detection_get_session" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "get" and "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    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.
  • 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, referrer, user agent, and …Reads text others writeNo findings

    Why it is in this group

    • The name "agent_detection_list_sessions" says "list": a word for reading.

    What it can reach

    • untrusted-inputThe description's first sentence says "list" and "website": it reads web pages, which anyone can write.
    Description, as the server wrote it
    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_list_sitesList this team's Agent Detection integrations.No findings

    Why it is in this group

    • The name "agent_detection_list_sites" says "list": a word for reading.
    Description, as the server wrote it
    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>.
  • analyze_mediaAnalyze media for structured intelligence: transcription, translation, language, speaker info, emotion, scene description, abnormalities, and misinformation analysis.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "analyze_media" says "analyze": a word for reading.

    What it can reach

    • untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

    Claude Code: ask, because it is tagged outbound.

    Description, as the server wrote it
    Analyze media for structured intelligence: transcription, translation, language, speaker info, emotion, scene description, abnormalities, and misinformation analysis. media_type: auto | audio | video | image.
  • get_detect_agent_runFetch a persisted Detect Agent investigation by run_id, including its full event transcript.No findings

    Why it is in this group

    • The name "get_detect_agent_run" says "get": a word for reading.
    Description, as the server wrote it
    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.
  • get_detectionFetch a detection by UUID, polling until it completes (bounded).No findings

    Why it is in this group

    • The name "get_detection" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a detection by UUID, polling until it completes (bounded). Use after detect_deepfake when a long job exceeded its wait budget.
  • get_text_detectionFetch a text detection by UUID, polling until it completes (bounded).No findings

    Why it is in this group

    • The name "get_text_detection" says "get": a word for reading.
    Description, as the server wrote it
    Fetch a text detection by UUID, polling until it completes (bounded). Use after detect_ai_text returned status 'processing' - typically a cold start.
  • list_detect_agentsList the managed Detect Agents — investigators that wrap detection in a multi-step workflow ending in a written assessment.No findings

    Why it is in this group

    • The name "list_detect_agents" says "list": a word for reading.
    Description, as the server wrote it
    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.
  • trace_audio_sourceGet the audio source-tracing report for a detection (which AI platform generated the fake audio).No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out5
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:10 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
8
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
yes
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.resemble.ai/mcp: tools/list returned 18 tools to an anonymous client, including detect_deepfake (write), detect_ai_text (write), ask_about_detection (write), detect_watermark (write), apply_watermark (write) and 3 more

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 1.4.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http resemble https://mcp.resemble.ai/mcp
claude mcp add --transport http resemble https://mcp.resemble.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__resemble__get_detection",
      "mcp__resemble__get_text_detection",
      "mcp__resemble__trace_audio_source",
      "mcp__resemble__list_detect_agents",
      "mcp__resemble__get_detect_agent_run",
      "mcp__resemble__agent_detection_list_sites",
      "mcp__resemble__agent_detection_get_analytics",
      "mcp__resemble__agent_detection_list_sessions",
      "mcp__resemble__agent_detection_get_session"
    ],
    "ask": [
      "mcp__resemble__detect_deepfake",
      "mcp__resemble__detect_ai_text",
      "mcp__resemble__analyze_media",
      "mcp__resemble__ask_about_detection",
      "mcp__resemble__detect_watermark",
      "mcp__resemble__apply_watermark",
      "mcp__resemble__run_detect_agent_investigation",
      "mcp__resemble__agent_detection_create_site",
      "mcp__resemble__agent_detection_update_site"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as resemble. Review it before you use it.

Capability tags behind 8 rules
  • mcp__resemble__detect_deepfake outbound
  • mcp__resemble__analyze_media untrusted-input, outbound
  • mcp__resemble__detect_watermark outbound
  • mcp__resemble__apply_watermark outbound
  • mcp__resemble__run_detect_agent_investigation outbound
  • mcp__resemble__agent_detection_get_analytics untrusted-input
  • mcp__resemble__agent_detection_list_sessions untrusted-input
  • mcp__resemble__agent_detection_get_session untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.resemble-ai/resemble-mcp/verify?hash=938de07c1a86d926d5eb03889d893193dc558e2273d5cdc956a849a1f33a65e3" | jq -e '.changed == false'

Pinned hash 938de07c1a86, from Nov 9, 2026, 20:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.resemble-ai/resemble-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.resemble-ai/resemble-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.resemble-ai/resemble-mcp.svg)](https://radar.anlyon.com/servers/io.github.resemble-ai/resemble-mcp)

Source: MCP Registry · repository. Synced Oct 28, 2026, 00:17 UTC.

Resemble AI MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Resemble AI MCP server safe?

No scan can promise that. What its definitions show: 18 tools, 8 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Resemble AI MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Resemble AI MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Resemble AI MCP server have?

18 tools: 8 write, 10 read. detect_deepfake, detect_ai_text, ask_about_detection, detect_watermark, apply_watermark, run_detect_agent_investigation, agent_detection_create_site, agent_detection_update_site and 10 more.

Does the Resemble AI MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Resemble AI MCP server send data to outside services?

5 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): detect_deepfake, analyze_media, detect_watermark, apply_watermark and run_detect_agent_investigation.

Has the Resemble AI MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 9, 2026.