MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Export LinkedIn, Sales Navigator and Apollo searches; find decision makers and verified work emails
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.
SCRUPP_API_KEY, SCRUPP_WAIT_SECONDSValues 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 …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"scrupp": {
"command": "npx",
"args": [
"-y",
"scrupp-mcp-server"
],
"env": {
"SCRUPP_API_KEY": "your-value",
"SCRUPP_WAIT_SECONDS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add scrupp --env SCRUPP_API_KEY=your-value --env SCRUPP_WAIT_SECONDS=your-value -- npx -y scrupp-mcp-serverFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"scrupp": {
"command": "npx",
"args": [
"-y",
"scrupp-mcp-server"
],
"env": {
"SCRUPP_API_KEY": "your-value",
"SCRUPP_WAIT_SECONDS": "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": {
"scrupp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"scrupp-mcp-server"
],
"env": {
"SCRUPP_API_KEY": "your-value",
"SCRUPP_WAIT_SECONDS": "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 one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
SCRUPP_WAIT_SECONDS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
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 7, 2026
The publisher (wismhero-maker) is not the repo owner (Wism-Corp); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 0 of 1 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: SCRUPP_API_KEY
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.2.3) reached the registry 24 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
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.
An MCP server over the Scrupp Jobs API, so an agent can export LinkedIn, Sales Navigator and Apollo searches, find decision makers, and find and verify work emails without anyone writing HTTP calls. Ships as scrupp-mcp-server on npm and in the official MCP registry as io.github.wismhero-maker/scrupp. Overview: https://scrupp.com/email-finder-mcp
Add https://mcp.scrupp.com/mcp as a custom connector in Claude and sign in to Scrupp. It finds and verifies work emails on any Scrupp plan, including the free one. Scrupp customers who want the full tool set use the private connector described in the setup guide. Setup steps, what each tool needs and troubleshooting: https://scrupp.com/docs/api/claude
/plugin install scrupp --marketplace Wism-Corp/scrupp-mcp-server
On Claude Code older than 2.1.275, in two steps:
/plugin marketplace add Wism-Corp/scrupp-mcp-server
/plugin install scrupp@scrupp
The plugin connects Claude Code to Scrupp's private hosted connector, with the same full tool set as the private Claude connector, so nothing is installed locally. The first time a tool runs, open /mcp, pick scrupp and sign in to Scrupp.
The plugin carries two things:
.mcp.json — the hosted connector above, signed in with OAuth.skills/scrupp-prospecting — how Claude should use the tools: check credits first, pick the tool from what the user has, export five records as a sample before the whole search, collect long jobs with scrupp_get_job, and what to say when a tool refuses.Check it before a release with claude plugin validate ..
{
"mcpServers": { "scrupp": { "command": "npx", "args": ["-y", "scrupp-mcp-server"], "env": { "SCRUPP_API_KEY": "sk_live_..." } } } }
SCRUPP_WAIT_SECONDS (default 120) caps how long a tool blocks. A job that outruns it comes back as { status: "running", job_id } with a note telling the agent to call scrupp_get_job — better than holding a conversation open for twenty minutes on a 2,500-record export.
| Tool | What it does |
|---|---|
scrupp_export_sales_navigator_search | People out of a Sales Navigator search URL |
scrupp_export_linkedin_search | People out of a LinkedIn people-search URL |
scrupp_run_apollo_search | People out of an Apollo search URL (needs a connected account) |
scrupp_enrich_linkedin_profiles | Full profile data for profile URLs |
scrupp_lookup_company | Company data by domain, LinkedIn URL or name |
scrupp_find_decision_makers | Who to write to at a company |
scrupp_find_emails | Verified work emails from name + domain |
scrupp_verify_emails | Deliverability check for addresses you already have (1 credit each) |
scrupp_get_job | Status and records for a job that was still running |
scrupp_credits | Remaining credits and plan |
Every tool carries a title and readOnlyHint / destructiveHint annotations — the Claude connectors directory rejects a server without them.
node src/http.js (or scrupp-mcp-http) serves the same server over Streamable HTTP at POST /mcp, stateless, with GET /health for a load balancer. PORT defaults to 8787. Each request authenticates with the caller's own key as Authorization: Bearer sk_live_...; the key is scoped to that request, so one process serves many accounts without mixing them up.
The hosted connector exposes a narrower tool set than the local server: email finding, email verification, job status and credits. The tools that gather data from LinkedIn (Sales Navigator, LinkedIn search, profile enrichment) or answer from the shared lead base (company lookup, decision makers), and the Apollo export, stay local-only — they run through accounts that are not the caller's, which is not something to put in a public directory listing.
Try it in Claude Code against a deployed instance:
claude mcp add --transport http scrupp https://mcp.scrupp.com/mcp \
--header "Authorization: Bearer sk_live_..."
A second endpoint serves a fuller tool set for Scrupp customers who add it by URL (Claude.ai: Settings → Connectors → Add custom connector; the address is in the setup guide at https://scrupp.com/docs/api/claude). It is not listed in the directory and works on every Scrupp plan. On top of the core tools it has the rest of the API: scrupp_build_sales_navigator_search (audience in words → a Sales Navigator search URL with the size Sales Navigator reports, no credits), scrupp_export_sales_navigator_search, scrupp_export_linkedin_search, scrupp_run_apollo_search, scrupp_enrich_linkedin_profiles (optionally with emails), scrupp_lookup_company and scrupp_find_decision_makers.
When the caller has a LinkedIn account with Sales Navigator connected with the Scrupp extension, all of them run only on that account. Without one, they run on Scrupp's shared account pool, which is open to paid plans. The Scrupp API decides this, not this server.
The OAuth resource is what tells the two apart: each endpoint's protected-resource metadata names its own resource, and app.scrupp.com issues the private connector's key (connector:claude-sn) only for the private resource. A key from the /mcp connector gets 403 on everything beyond email finding even if it is sent to the private endpoint.
Users of Claude.ai, Claude Desktop and Claude Code don't paste a key: they press Connect, sign in to Scrupp and allow access. The server advertises its authorization server at /.well-known/oauth-protected-resource (RFC 9728) and answers an unauthenticated request with 401 and a WWW-Authenticate header pointing there. The authorization server itself lives in the Scrupp app at app.scrupp.com (/oauth/register, /oauth/authorize, /oauth/token); the access token it issues is an ordinary Scrupp API key marked connector:claude, which the API restricts to the four tools above. Access tokens last an hour, so the server checks the token before each request (cached for a minute) and answers 401 invalid_token when it has expired, which is what makes the client refresh it.
| Variable | Default | Meaning |
|---|---|---|
PORT | 8787 | Listen port |
MCP_PUBLIC_URL | https://mcp.scrupp.com | Public URL of this server, used in the metadata |
SCRUPP_AUTH_SERVER_URL | https://app.scrupp.com | Where OAuth tokens are issued |
SCRUPP_API_URL | https://api.scrupp.com/api/v1 | Scrupp API the tools call |
Tool descriptions are written for a model, not a human: they say when to reach for the tool, not just what it does. That is the whole ranking signal in a registry — a listed server with vague descriptions gets picked and then misused.
Wism-Corp/scrupp-mcp-server — the MCP registry validates ownership from the repository and the mcpName in package.json.npm publish --access public with provenance from GitHub Actions, the same workflow shape as n8n-nodes-scrupp. npx @modelcontextprotocol/publisher login github
npx @modelcontextprotocol/publisher publish
It reads `server.json`, checks the npm package carries the matching `mcpName`, and
lists the server.
npm install
SCRUPP_API_KEY=... npx @modelcontextprotocol/inspector node src/index.js
Run scrupp_credits first (free), then scrupp_find_emails with two people — the cheapest call that exercises create → poll → result.