MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Measure whether AI assistants mention your brand. Reports, model answers, scans, free site tools.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
AuthorizationValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Run this in your terminal
claude mcp add --transport http whereamimentioned https://whereamimentioned.com/api/mcp --header 'Authorization: your-value'Fill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"whereamimentioned": {
"url": "https://whereamimentioned.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"whereamimentioned": {
"type": "http",
"url": "https://whereamimentioned.com/api/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This address needs a key in a request header, which the add-connector menu cannot set. Use Claude Code, Cursor or VS Code instead.
Your choice stays on this device in a cookie; no account needed.
Authorization secret HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 7, 2026. The maker wrote them, not us; we show them as plain text.
check_ai_crawler_accessCheck whether a site's robots.txt allows or blocks each known AI crawler (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and about thirty others), with the exact rule and line that decided it.
validate_llms_txtFetch and validate a site's llms.txt: findings with severity and line numbers, a 0 to 100 score, section and entry counts, whether the linked URLs resolve, and whether a sibling llms-full.txt exists.
generate_llms_txtCrawl a site and generate an llms.txt. depth "index" produces the link index (up to 30 pages); depth "full" produces llms-full.txt with extracted page content (up to 20 pages).
generate_sitemapCrawl a site (up to 200 pages, sitemap-first with a link-following fallback) and return a valid sitemap.xml, with lastmod only where it was genuinely observed.
analyze_content_chunkingAnalyze how well a page is chunked for retrieval: per-heading sections with word and token counts, findings by severity, strengths, a score and the top fixes.
validate_structured_dataFetch a page, validate its JSON-LD entities against the schema.org types that matter for AI visibility, and report per-entity findings with severity, entity counts and a score. Also reports how many microdata and RDFa annotations are present, without validating them.
check_meta_descriptionAnalyze a page's title, meta description, og:description and opening paragraph: character and pixel widths, where desktop and mobile truncate, a score and per-check findings.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 8, 2026
The registry name was verified against the domain whereamimentioned.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 253 ms (HTTP 200)
No sign-in needed
Read 7 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: Authorization
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (0.1.0-rc.1) reached the registry today.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: MCP YouTube Transcript, Google Analytics MCP, BibiGPT YouTube Video Summarizer
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
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.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
This repository is generated. It is a one-way copy of the packages/ directory of a private repository, rebuilt from scratch and force-pushed on every release tag. Nothing here is edited by hand: a commit made in this repository is destroyed by the next sync, with no warning and no merge, and a pull request opened here is opened against a copy of a file its author cannot reach and will be destroyed the same way. Please do not send pull requests to this repository. The root package.json, vitest.config.mts and pnpm-lock.yaml are generated by the same sync and exist only so that this tree installs, typechecks, tests and builds on its own.
Three npm packages, versioned and released together, for whereamimentioned, which measures whether AI assistants mention your brand.
packages/cli, published as @whereamimentioned/cli. The wam command line: the free site checks that need no account, scans and reports from a terminal or from CI, and the installer for the MCP server. Documented at whereamimentioned.com/docs/cli.packages/mcp-stdio, published as @whereamimentioned/mcp. A small stdio bridge for MCP clients that cannot add a remote URL. It forwards each request to the hosted server at https://whereamimentioned.com/api/mcp and holds no tool definitions of its own. Documented at whereamimentioned.com/docs/mcp.packages/api-client, published as @whereamimentioned/api-client. The typed client and response types for the REST API at https://whereamimentioned.com/api/v1, described by its OpenAPI document. The other two packages are built against it.None of the three contains server code, database access or a secret. Every request they make goes to https://whereamimentioned.com.
Releases run from this repository so that npm provenance and GitHub artifact attestations are generated. Each release tag (cli-v*) carries a GitHub Release with the CLI tarball and a SHA256SUMS file, and the npm packages carry provenance pointing back here.
Open an issue in this repository's issue tracker. Issues are not part of the synced tree, so they survive the sync; pull requests do not. For anything involving your account or your data, use whereamimentioned.com/contact instead of a public issue.