Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Beschreibung vom Entwickler (englisches Original)
Resemble AI: deepfake, AI-text, and site agent detection, Detect Agents, intelligence, watermarks.
Diese drei werden nie zu einer Punktzahl zusammengefasst: Meinungen, Messungen und Beliebtheit sind verschiedene Dinge.
Für diesen Server haben wir noch keine Zusammenfassung in einfacher Sprache geschrieben. Unten stehen die Fakten, die wir aus der Registry gelesen haben.
Wähle die KI-App, die du nutzt, und kopiere die Einstellungen.
Du brauchst
Welche App nutzt du?
Wähle oben deine App. Wir merken sie uns, damit der Button beim nächsten Mal „In … installieren“ anzeigt.
Funktioniert in Claude im Web, auf dem Desktop und auf dem Handy:
https://mcp.resemble.ai/mcpFühre das in deinem Terminal aus
claude mcp add --transport http resemble https://mcp.resemble.ai/mcpIn .cursor/mcp.json in deinem Projekt oder in ~/.cursor/mcp.json einfügen
{
"mcpServers": {
"resemble": {
"url": "https://mcp.resemble.ai/mcp"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
In .vscode/mcp.json in deinem Projekt einfügen
{
"servers": {
"resemble": {
"type": "http",
"url": "https://mcp.resemble.ai/mcp"
}
}
}Dein Browser fragt, ob er die App öffnen darf, dann zeigt die App die Einstellungen und bittet dich um Bestätigung. Schlüsselwerte bleiben leer, damit du sie selbst einträgst.
ChatGPT verbindet sich nur mit Servern im Internet:
https://mcp.resemble.ai/mcpMenünamen können sich je nach Tarif und mit der Zeit leicht unterscheiden.
Deine Auswahl bleibt in einem Cookie auf diesem Gerät; kein Konto nötig.
Diese Einstellungen werden aus dem Registry-Eintrag des Entwicklers erzeugt. Wenn in der README etwas anderes steht, folge der README.
Tool-Namen und -Beschreibungen genau so, wie der Server sie am 7. Nov. 2026 gemeldet hat. Geschrieben hat sie der Entwickler, nicht wir; wir zeigen sie als reinen Text.
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, confidence score, and full result. Optional flags add media intelligence, audio source tracing, visualization, reverse image search
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 back as prediction 'uncertain' with no model call - concatenate several messages from the same author to reach the minimum. Retur
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 misinformation analysis. media_type: auto | audio | video | image.
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_tracing and labeled the audio fake.
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_id plus this team's run allowance (free_runs_remaining, entitled), which is worth checking before starting a run.
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, review_insurance_claim, verify_breaking_news, verify_document, verify_evidence, verify_id (confirm with list_detect_agents). query
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, or to re-read an earlier investigation.
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 assistant browsing on someone's behalf). Each integration is one website, with the domains its publishable key works on and the o
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 domain, e.g. example.com. If the team already has an integration for that domain, the existing one is returned instead of a dup
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. domains replaces the whole list, so include every domain to keep; at least one is required.
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 (human, computer_use_agent, browser_automation, scripted_client), and breakdowns by page, day, and network. Use this to show ho
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 duration. Same filters as agent_detection_get_analytics plus a free-text search. per_page max 100.
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. When the visit was recorded, the raw event stream is available; it is omitted unless include_events is true, and then capped at the
Wir prüfen Informationen, die jeder sehen kann; den Code haben wir nicht gelesen. Checks, die nicht zutreffen, werden nicht mitgezählt. · Geprüft am 8. Nov. 2026
Der Registry-Name wurde mit dem GitHub-Konto resemble-ai bestätigt, dem das Repo gehört
Dieses Repo haben wir noch nicht von GitHub gelesen
Dieses Repo haben wir noch nicht von GitHub gelesen
Antwort in 551 ms (HTTP 200)
Keine Anmeldung nötig
Wir haben 18 Tool-Beschreibungen gelesen und keine versteckten Anweisungen an die KI gefunden
Verglichen mit allen aktiven Servern dieser Kategorie in der Registry. Sterne zählen nur, wenn dem Herausgeber das Repo gehört.
Er hat 3 von 3 zutreffenden Basischecks bestanden. Den Code haben wir nicht gelesen. Bevor du einen Schlüssel oder Token hinzufügst, sieh nach, welche Zugriffe der Server verlangt, und nutze einen Schlüssel, der nur die Berechtigungen hat, die du brauchst.
Die Registry nennt keinen erforderlichen Schlüssel, manche Server bitten dich aber bei der ersten Nutzung, dich anzumelden.
Er läuft in der Cloud des Entwicklers. Du verbindest dich übers Internet, ohne etwas zu installieren, aber was du sendest, läuft über die Server des Entwicklers.
Das GitHub-Repo wurde zuletzt – geändert, und die neueste Version (1.4.0) kam vor 11 Tagen in die Registry.
Apps, die MCP unterstützen, etwa Claude Desktop, Claude Code, Cursor und VS Code. Er verbindet sich per URL, also funktionieren auch Apps, die Remote-MCP-Server akzeptieren, zum Beispiel ChatGPT im Entwicklermodus.
In derselben Kategorie: Spec Driven Development, Remote Desktop Commander, Tethered Trust
Server derselben Kategorie von anderen Entwicklern, sortiert nach Sternen.
So liest du eine Karte:↓ Downloads pro Wochei★ GitHub-SterneiDrei Säulen: Bewertungen · Checks · NutzungiAktualisiert = neueste Version in der Registry veröffentlichti
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
Unverändert aus dem Repo des Entwicklers übernommen. PopNx MCP hat den Inhalt weder geprüft noch empfiehlt es ihn. HTML, Bilder und Skripte wurden entfernt. Links führen von dieser Website weg.
Official MCP server exposing Resemble AI documentation as resources and tools. Connect to Cursor, Claude Code, or any MCP-compatible client to enable your coding assistant to access Resemble AI docs during development.
This is the official Resemble AI MCP server. It implements the Model Context Protocol (stdio transport) to serve documentation from docs/pages/ as queryable resources. The server aggregates docs by topic and provides full-text search across all MDX files.
What it provides:
Once connected, your coding assistant can query Resemble AI documentation programmatically. You can vibe code complete applications—your assistant has instant access to guides, tutorials, and exact API schemas for accurate code generation.
git clone https://github.com/resemble-ai/resemble-mcp.git
cd resemble-mcp
python3 -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate
pip install -r requirements.txt
Cursor: Add to ~/.cursor/mcp.json:
{
"mcpServers": { "resemble-ai-docs": { "command": "/path/to/resemble-mcp/venv/bin/python", "args": ["/path/to/resemble-mcp/server.py"] } } }
Claude Code / Claude Desktop: Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or equivalent location for your OS:
{
"mcpServers": { "resemble-ai-docs": { "command": "/path/to/resemble-mcp/venv/bin/python", "args": ["/path/to/resemble-mcp/server.py"] } } }
Note: Use absolute paths. Replace
/path/to/resemble-mcpwith your actual path.
Restart your MCP client to load the server. Tools will be available after restart.
resemble_docs_lookupReturns aggregated documentation for a topic. Accepts topic ID and returns all related pages concatenated.
Parameters:
topic (string, required): One of: voice-cloning, text-to-speech, speech-to-speech, speech-to-text, getting-started, voice-design, streaming, detect, agents, sdks, projects-clips, audio-tools, ssmlReturns: Markdown content with all pages for the topic.
resemble_searchFull-text search across all documentation pages. Returns matching pages with snippets.
Parameters:
query (string, required): Search querylimit (integer, optional): Max results (default: 5)Returns: List of matching pages with titles, paths, and content snippets.
resemble_get_pageRetrieves a specific documentation page by path.
Parameters:
path (string, required): Page path relative to docs/pages/ (e.g., getting-started/quickstart)Returns: Full page content in Markdown.
resemble_list_topicsLists all available topic IDs with descriptions.
Returns: Markdown list of topics.
resemble_api_endpointGet detailed OpenAPI specification for a specific API endpoint. Returns exact request/response schemas, parameters, and types.
Parameters:
method (string, required): HTTP method (GET, POST, PUT, PATCH, DELETE)path (string, required): API endpoint path (e.g., /synthesize, /voices)Returns: Endpoint specification with schemas, parameters, and response formats.
resemble_api_searchSearch the OpenAPI spec for endpoints matching a query.
Parameters:
query (string, required): Search query (e.g., voice, streaming, agent)Returns: List of matching endpoints with methods, paths, and summaries.
Once configured, your coding assistant (Cursor, Claude Code, etc.) can call these tools directly. Example use cases:
Building a voice cloning app:
{
"name": "resemble_docs_lookup", "arguments": { "topic": "voice-cloning" } }
Searching for streaming implementation:
{
"name": "resemble_search", "arguments": { "query": "websocket streaming", "limit": 5 } }
Getting exact API schema for implementation:
{
"name": "resemble_api_endpoint", "arguments": { "method": "POST", "path": "/synthesize" } }
Finding all voice-related API endpoints:
{
"name": "resemble_api_search", "arguments": { "query": "voice" } }
Your assistant uses these tools automatically when you ask it to build features. For example, "build me a TTS streaming service" triggers resemble_docs_lookup for the text-to-speech topic, and may use resemble_api_endpoint to get exact request schemas for accurate implementation.
resemble-mcp/
├── server.py # MCP server implementation ├── docs/ │ └── pages/ # MDX documentation files │ ├── getting-started/ # Auth, quickstart, basics │ ├── voice-generation/ # TTS, STT, S2S │ ├── voice-creation/ # Voice cloning, recordings │ ├── agents/ # AI agents │ ├── detect/ # Deepfake detection │ └── guides/ # Step-by-step tutorials └── openapi/ └── openapi.yml # OpenAPI 3.0 specification
Works with any client implementing the Model Context Protocol:
The server uses stdio transport (reads from stdin, writes to stdout) as per MCP specification.
# Run server directly (for testing/debugging)
python server.py
Architecture:
server.pydocs/pages/ (MDX files)openapi/openapi.yml (OpenAPI 3.0)TOPICS dictServer not loading:
mcp package is installed: pip show mcpTools not appearing:
python server.pySearch returns no results:
resemble_docs_lookup with topic ID for guaranteed resultsresemble_list_topicsMIT License - see LICENSE for details.