MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Funding rounds, LinkedIn data and actions, email verification and cited research briefs.
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.
PROSPECTAPIS_API_KEY, PROSPECTAPIS_BASE_URL, 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.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"prospectapis": {
"command": "npx",
"args": [
"-y",
"prospectapis-mcp"
],
"env": {
"PROSPECTAPIS_API_KEY": "your-value",
"PROSPECTAPIS_BASE_URL": "your-value"
}
}
}
}Run this in your terminal
claude mcp add --transport http prospectapis https://api.prospectapis.com/mcp --header 'Authorization: your-value'claude mcp add prospectapis --env PROSPECTAPIS_API_KEY=your-value --env PROSPECTAPIS_BASE_URL=your-value -- npx -y prospectapis-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"prospectapis": {
"url": "https://api.prospectapis.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"prospectapis": {
"command": "npx",
"args": [
"-y",
"prospectapis-mcp"
],
"env": {
"PROSPECTAPIS_API_KEY": "your-value",
"PROSPECTAPIS_BASE_URL": "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": {
"prospectapis": {
"type": "http",
"url": "https://api.prospectapis.com/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}Paste into .vscode/mcp.json in your project
{
"servers": {
"prospectapis": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"prospectapis-mcp"
],
"env": {
"PROSPECTAPIS_API_KEY": "your-value",
"PROSPECTAPIS_BASE_URL": "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.
PROSPECTAPIS_BASE_URL envAuthorization secret required HTTP headerThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
The server asks you to sign in before it lists its tools.
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 registry name was verified against the domain prospectapis.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 472 ms (HTTP 401)
Declares OAuth sign-in, so your AI app can take you to log in
Not checked yet; we read the tool list when we check the endpoint
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: PROSPECTAPIS_API_KEY, Authorization
Either way works: install it on your computer or connect to the cloud version.
The GitHub repo last changed –, and the latest version (0.17.1) reached the registry yesterday.
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.
prospectapis-mcp is the MCP server for ProspectAPIs (https://prospectapis.com), for sales and prospecting teams and the AI agents they run in Claude Code, Claude Desktop, Cursor and other MCP clients. It gives your agent twenty-five tools over the ProspectAPIs API: search funding rounds by date, round, amount, company, investor and country, get new matching rounds pushed to your webhook, verify, find and bulk-check email addresses, report what bounced, and order a cited research brief on any company or person. Funding records carry the public announcement URL when there is one. Every account starts with a free $1 balance and no card: records cost $0.02, an email check $0.004 and a completed brief $0.15, with no seats and no subscription. It needs Node.js 22 or later.
Install (Claude Code): claude mcp add prospectapis -e PROSPECTAPIS_API_KEY=pa_live_... -- npx -y prospectapis-mcp
Other clients: run npx -y prospectapis-mcp with PROSPECTAPIS_API_KEY from https://prospectapis.com
Website: https://prospectapis.com/mcp
| Tool | Endpoint | Cost |
|---|---|---|
funding_search | GET /v1/funding | $0.02 per record returned; no match is free |
funding_get | GET /v1/funding/:id | $0.02 when found; a missing id is free |
research_submit | POST /v1/research | one research at research_price_usd (see account_balance), charged only when the brief completes; refunded on failure |
research_get | GET /v1/research/:id | free; poll until status is completed or failed |
email_verify | POST /v1/email/verify | $0.004 per valid or invalid result; catch-all and unknown are free; 1 to 25 addresses a call |
email_verify_stats | GET /v1/email/verify/stats | free |
email_outcomes_report | POST /v1/email/outcomes | free; 1 to 100 outcomes a call |
email_verify_job_create | POST /v1/email/verify/jobs | free to start; $0.004 per valid or invalid result as it is checked; up to 50,000 addresses |
email_verify_job_get | GET /v1/email/verify/jobs/:id | free |
email_verify_job_results | GET /v1/email/verify/jobs/:id/results | free; 1,000 a page |
watchlist_create, watchlist_list, watchlist_get, watchlist_deliveries, watchlist_test, watchlist_delete | /v1/watchlists | free to manage; a delivered event costs one record, only when your webhook answers 2xx |
account_balance | GET /v1/account | free |
feedback_send | POST /v1/feedback | free; reports a bug, wrong field or missing capability to the team (10 an hour per key) |
pricing_get | GET /pricing | free, no key needed; the live price list |
api_version | GET /v1/version | free, no key needed |
funding_search filters: since, until (YYYY-MM-DD), round (comma list such as seed,series_a), min_amount_usd, max_amount_usd, company, domain, investor, country, limit (1 to 100) and cursor (the previous page's next_cursor, passed back unchanged).
research_submit takes exactly one prospect identifier (domain, website_url, company_name, company_linkedin_url, a work email or linkedin_url), or person_name with company_name, plus an optional context (your own product, at most 1,000 characters) and purpose (account_research, pre_call or outreach). It returns a research_id at once; a brief takes 20 to 90 seconds.
email_verify takes emails, a list of 1 to 25 addresses. Each result has status (valid, invalid, catch-all or unknown), reason, reason_text, score (0 to 100), recommendation (send, send_with_caution, retry_later or do_not_send), charged, flags, smtp_code and catch_all_tier. If the balance covers only some addresses, the rest come back unknown with reason not_checked_insufficient_credits and are not charged.
| Variable | Required | Default |
|---|---|---|
PROSPECTAPIS_API_KEY | yes (all tools except pricing_get and api_version) | none |
PROSPECTAPIS_BASE_URL | no | https://api.prospectapis.com |
Client config (for example claude_desktop_config.json):
{
"mcpServers": { "prospectapis": { "command": "npx", "args": ["-y", "prospectapis-mcp"], "env": { "PROSPECTAPIS_API_KEY": "pa_live_..." } } } }
Claude Code: claude mcp add prospectapis -e PROSPECTAPIS_API_KEY=pa_live_... -- npx -y prospectapis-mcp.
Where does the funding data come from? Records carry the public announcement URL when there is one.
What is free? A $1 balance when you sign up (about 50 funding records, 250 email checks or 6 research briefs), any search that matches nothing, catch-all and unknown email results, watchlist management, and the balance, pricing and version tools.
Which clients work? Claude Code, Claude Desktop, Cursor and any client that reads an mcpServers config, through npx -y prospectapis-mcp.
cd mcp
npm install npm test # mocked fetch over an in-memory MCP transport, no network npm run check
The package is versioned independently of the API (SemVer, CHANGELOG.md in this folder). It is marked private so it cannot be published by accident; publishing is done only from the product's own npm identity.