MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Descripción del creador (original en inglés)
SEO data your AI can cite: Search Console, GA4, keywords, backlinks, SERPs and AI visibility.
Estos tres nunca se combinan en una sola puntuación: las opiniones, las mediciones y la popularidad son cosas distintas.
Todavía no escribimos un resumen sencillo para este. Abajo están los datos que leímos del registro.
Elige la app de IA que usas y copia la configuración.
Necesitas
¿Qué app usas?
Elige tu app arriba. La recordamos, así que la próxima vez el botón dirá “Instalar en …”.
Funciona en Claude para web, escritorio y móvil:
https://vouchedhq.com/mcpEjecuta esto en tu terminal
claude mcp add --transport http vouched https://vouchedhq.com/mcpPégalo en .cursor/mcp.json de tu proyecto, o en ~/.cursor/mcp.json
{
"mcpServers": {
"vouched": {
"url": "https://vouchedhq.com/mcp"
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
Pégalo en .vscode/mcp.json de tu proyecto
{
"servers": {
"vouched": {
"type": "http",
"url": "https://vouchedhq.com/mcp"
}
}
}Tu navegador te pide permiso para abrir la app; luego la app muestra la configuración y te pide confirmar. Los valores de las claves quedan vacíos para que los completes tú.
ChatGPT solo se conecta a servidores en internet:
https://vouchedhq.com/mcpLos nombres de los menús pueden variar un poco según el plan y con el tiempo.
Tu elección se guarda en una cookie en este dispositivo; no necesitas cuenta.
Esta configuración se genera a partir de la ficha del creador en el registro. Si el README dice otra cosa, sigue el README.
Todavía no hemos leído la lista de herramientas de este servidor; revisamos los endpoints por turnos.
Revisamos información que cualquiera puede ver; no hemos leído el código. Las revisiones que no aplican no se cuentan. · Revisado el 7 nov 2026
Quien lo publicó (vouchedhq.com) no es el dueño del repo (muditjuneja); puede que otra persona lo haya listado
Todavía no hemos leído este repo en GitHub
Todavía no hemos leído este repo en GitHub
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; revisamos los endpoints por turnos
Aún sin revisar; leemos la lista de herramientas cuando revisamos el endpoint
Comparado con todos los servidores activos de esta categoría en el registro. Las estrellas solo cuentan cuando quien lo publica es dueño del repo.
Superó 0 de 1 revisiones básicas aplicables. No hemos leído el código. Antes de agregar una clave o un token, revisa qué acceso pide el servidor y usa una clave que tenga solo los permisos que necesitas.
El registro no indica ninguna clave obligatoria, aunque algunos servidores te piden iniciar sesión la primera vez que los usas.
Se ejecuta en la nube del creador. Te conectas por internet sin instalar nada, pero lo que envías pasa por los servidores del creador.
El repo de GitHub cambió por última vez –, y la última versión (0.1.0) llegó al registro hace 41 días.
Las apps compatibles con MCP, como Claude Desktop, Claude Code, Cursor y VS Code. Se conecta por URL, así que también funcionan las apps que aceptan servidores MCP remotos, como ChatGPT en modo desarrollador.
En la misma categoría: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Servidores de la misma categoría hechos por otros creadores, ordenados por estrellas.
Cómo leer una tarjeta:★ Estrellas de GitHubiTres pilares: reseñas · revisiones · usoiActualizado = fecha en que se publicó la última versión en el registroi
An MCP server retrieving transcripts of YouTube videos
GA4 MCP server for AI agents: schema discovery, server-side aggregation, analysis-ready defaults.
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
Copiado tal cual del repo del creador. PopNx MCP no lo ha revisado ni lo respalda. Se quitaron HTML, imágenes y scripts. Los enlaces llevan fuera de este sitio.
Vouched
SEO data your AI can cite. An open-source MCP server for Search Console, Google Analytics, keywords, backlinks, live Google results and AI answer visibility.
Website · Tools · Self-host · MIT license
Ask Claude, ChatGPT or Cursor "why did our clicks drop last month?" or "which keywords does our competitor rank for that we don't?" and it answers from real data instead of guessing.
Every tool returns the same JSON envelope. Each fact in it says where it came from, how confident it is and when it was observed, so the agent (and you) can tell a Search Console number from an index estimate.
Hosted at [vouchedhq.com](https://vouchedhq.com). Add https://vouchedhq.com/mcp as a connector in your AI client and sign in. Your own Google data is free; live market data comes from DataForSEO, needs a Pro or Team plan and is billed at cost. See pricing.
Self-hosted. Run the same server on your own Cloudflare account, with your own Google OAuth client and, if you want market data, your own DataForSEO key. No markup, no account with us. See docs/SELF_HOST.md.
Both run the same code and expose the same tools.
19 tools, all read-only. Nothing is ever written to Google or to any site.
Your own data (free; needs a Google connection)
| Tool | What it answers |
|---|---|
get_search_performance | Clicks, impressions, CTR and position by query, page, date, country or device, with period-over-period changes |
inspect_indexing | Is this URL indexed, which canonical did Google pick, when was it last crawled |
list_sitemaps | Submitted sitemaps, with errors, warnings and URL counts |
get_website_analytics | Sessions, users and engagement from GA4 |
Market data (from DataForSEO: on a Pro or Team plan when hosted, with your own key when self-hosted)
| Tool | What it answers |
|---|---|
inspect_domain | A domain's organic traffic, ranking keywords and main competitors |
discover_competitors | Who competes with a site for the same keywords |
research_keywords | Keyword ideas around seed terms, with volume, difficulty, CPC and intent |
inspect_keyword | How big and how hard one keyword is |
inspect_serp | Who ranks on Google for a query right now, plus AI Overviews and other features |
inspect_search_visibility | Where a domain ranks for a list of keywords |
inspect_page | Keywords and traffic for a single URL |
compare_keyword_coverage | Keywords competitors rank for that you don't |
inspect_backlinks | Authority, referring domains, anchors and individual backlinks |
compare_backlink_gap | Sites linking to competitors but not to you |
discover_ai_citations | Which sites AI answers cite for a topic |
inspect_ai_visibility | How often a domain is mentioned in AI answers compared with competitors |
Utilities
| Tool | What it does |
|---|---|
describe_capabilities | What's enabled on this server, and what each tool costs |
list_websites | Your tracked websites and their Google connections |
export_dataset | The full result behind a truncated response, kept for 7 days |
Each tool has a page with inputs, outputs and an example response at vouchedhq.com/tools. The generated reference is docs/TOOLS.md.
Vouched has no search index or web crawler of its own. What Vouched builds and runs is the MCP server: sign-in, the response envelope, provenance and confidence on every fact, caching, period comparisons, exports and billing. The data behind the tools comes from your Google account or from DataForSEO:
| Tools | Upstream API | Source class in provenance |
|---|---|---|
get_search_performance, inspect_indexing, list_sitemaps | Google Search Console API (Search Analytics, URL Inspection, Sitemaps), read with your own Google sign-in | webmaster_console |
get_website_analytics | Google Analytics Data API (GA4), same sign-in | analytics_property |
inspect_domain, discover_competitors, research_keywords, inspect_keyword, inspect_page, compare_keyword_coverage | DataForSEO Labs API | search_index |
inspect_serp | DataForSEO SERP API (live Google results) | live_serp |
inspect_search_visibility | DataForSEO Labs API, plus the SERP API when asked to re-check positions live | search_index, live_serp |
inspect_backlinks, compare_backlink_gap | DataForSEO Backlinks API | backlink_index |
discover_ai_citations, inspect_ai_visibility | DataForSEO AI Optimization API (LLM Mentions, for Google AI Overviews or ChatGPT) | ai_answer |
describe_capabilities, list_websites, export_dataset | None: Vouched's own data | none |
On the hosted Pro and Team plans, market-data calls go through Vouched's DataForSEO account and count against your plan's included market data, priced at DataForSEO's cost (see pricing). Self-hosted, they use your own DataForSEO key. DataForSEO only receives the keywords, domains and URLs a request asks about, never your Google data.
A trimmed get_search_performance result:
{
"schema_version": "ofe/1.0", "domain": "gsc", "data": { "domain": "xmit.sh", "startDate": "2026-08-28", "endDate": "2026-09-24", "dimensions": ["query"] }, "facts": [ { "type": "gsc.query_performance", "subject": ["property:...", "keyword:any:GLOBAL:transactional email api"], "data": { "dimensions": { "query": "transactional email api" }, "clicks": 41, "impressions": 3120, "ctr": 0.013, "position": 8.2 }, "provenance": { "source_class": "webmaster_console", "method": "gsc.searchAnalytics.query", "confidence": 1, "observed_at": "2026-09-25T08:00:00Z", "cache_hit": false } } ], "deltas": [{ "fact_type": "gsc.query_performance", "field": "clicks", "previous": 29, "current": 41 }], "coverage": { "returned": 25, "total": null, "scope_note": "capped at 25 rows; more are available via export_dataset" }, "resources": [{ "uri": "mcpseo://gsc/...", "description": "Up to 1000 rows for this same query" }], "next_actions": [] }
deltas compare with the previous period, coverage says what the result leaves out, resources holds the rest, and next_actions suggests follow-up calls when there are useful ones. The full shape is in docs/OFE_ENVELOPE.md.
Hosted:
# Claude Code: the plugin (MCP server plus an SEO analysis skill)
claude plugin marketplace add muditjuneja/vouched claude plugin install vouched@vouched
claude mcp add --transport http vouched https://vouchedhq.com/mcp
gemini extensions install https://github.com/muditjuneja/vouched
In Claude or ChatGPT, add https://vouchedhq.com/mcp as a custom connector. In Cursor, add it to ~/.cursor/mcp.json:
{ "mcpServers": { "vouched": { "url": "https://vouchedhq.com/mcp" } } }
Your client opens a sign-in page the first time (standard MCP OAuth). Clients that can only send a header can use an API key from the dashboard instead.
Self-hosted, point the client at your Worker's /mcp URL with your bearer token; see docs/SELF_HOST.md.
npm install
cp .dev.vars.example .dev.vars # MCP_BEARER_TOKEN at minimum npm run db:migrate:local npm run dev # http://localhost:8787/mcp
npm test npm run typecheck npm run lint
Set DATAFORSEO_BASE_URL=https://sandbox.dataforseo.com while developing: DataForSEO's sandbox is free and returns dummy data in the real response shape.
Built on Cloudflare Workers with Hono, D1, R2 and KV. No Google SDK: the Google APIs are called directly.
Google data is read only when you ask for it and is covered by Google's Limited Use requirements. It is never sold, used for ads or used to train AI models. See the privacy policy.
Issues and pull requests are welcome. For the hosted service, email hello@vouchedhq.com.
MIT