MCP YouTube Transcript
An MCP server retrieving transcripts of YouTube videos
Description from the maker (original English)
Pirsch Analytics with natural language queries and trend analysis
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.
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": {
"pirsch": {
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}Run this in your terminal
claude mcp add pirsch -- npx -y @verygoodplugins/mcp-pirschPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"pirsch": {
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}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": {
"pirsch": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@verygoodplugins/mcp-pirsch"
]
}
}
}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.
These 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 registry name was verified with the GitHub account verygoodplugins, which owns the repo
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 1 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.
The registry does not list a required key, though some servers ask you to sign in on first use.
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 (0.2.0) reached the registry 2 months 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.
A focused, read-only Model Context Protocol server for Pirsch Analytics API v1. It uses MCP SDK v2 and returns both structured results and JSON text for every successful tool call.
{
"mcpServers": { "pirsch": { "command": "npx", "args": ["-y", "@verygoodplugins/mcp-pirsch@latest"], "env": { "PIRSCH_CLIENT_ID": "your-read-only-oauth-client-id", "PIRSCH_CLIENT_SECRET": "your-oauth-client-secret", "PIRSCH_DEFAULT_DOMAIN_ID": "optional-default-domain-id" } } } }
PIRSCH_DEFAULT_DOMAIN_ID is optional. When it is unset, every query tool requires domainId; the server never picks the first accessible domain. Use pirsch_list_domains to discover IDs safely.
Optional PIRSCH_TIMEZONE supplies the default timezone for requests that do not explicitly include timezone.
| Tool | Purpose |
|---|---|
pirsch_list_domains | Lists only id, hostname, display name, and timezone. |
pirsch_query_statistics | Reads one documented v1 metric, with dates and filters. |
pirsch_list_filter_options | Lists allowed values for a documented filter dimension. |
pirsch_compare_periods | Compares actual totals and visitor series for two periods. |
All tools are read-only. They return structuredContent matching their output schema as well as an equivalent JSON text block. Input or API failures use MCP isError: true and do not expose credentials or raw upstream bodies.
pirsch_query_statistics accepts a metric, optional domainId, and flat camel-case filters. Most metrics require ISO dates:
{
"metric": "pages", "domainId": "your-domain-id", "from": "2026-08-01", "to": "2026-08-23", "limit": 20, "sort": "visitors", "direction": "desc" }
The server maps public camel-case fields such as eventMetaKey, entryPath, operatingSystem, and utmCampaign to Pirsch's documented API-v1 parameter names. limit is constrained to 1–100 and active visitor start to 0–3600 seconds.
Metrics include totals, visitors, pages and entry/exit pages, session and page duration, goals, events and event metadata, growth, active visitors, time breakdowns, acquisition, browser/device, geographic, UTM, tags, keywords, funnels, sessions, and session details. session_details requires both visitorId and sessionId; event-specific metrics require event.
Provide a named period (today, yesterday, week, lastWeek, month, or lastMonth) or both explicit date pairs:
{
"domainId": "your-domain-id", "from": "2026-08-01", "to": "2026-08-07", "compareFrom": "2026-07-25", "compareTo": "2026-07-31", "scale": "day" }
The response compares /statistics/total and retains the two /statistics/visitor series; it does not estimate totals by summing charts.
Version 1.0 intentionally replaces the former 17-tool interface. There are no default aliases because aliases would keep unsafe domain-selection and ambiguous input behavior alive.
| Previous tools | Replacement |
|---|---|
pirsch_overview, pirsch_total, pirsch_pages, pirsch_events, and other statistic tools | pirsch_query_statistics with metric |
pirsch_utm | pirsch_query_statistics with one of the utm_* metrics |
pirsch_compare | pirsch_compare_periods |
| Domain discovery | pirsch_list_domains |
Input names are now camel-case and flat (domainId, compareFrom, eventMetaKey), not domain_id, nested filter, or compatibility aliases.
npm install
npm run typecheck npm run lint npm test npm run build npx -y @modelcontextprotocol/inspector@latest --cli node dist/index.js --method tools/list --format json
The release workflow publishes to npm with trusted publishing and then publishes the same tagged manifest to the MCP Registry through GitHub OIDC. Local development and CI never publish anything.
For bugs and feature requests, open an issue in this repository. Pirsch questions are best answered through the Pirsch documentation; package support is maintained by Very Good Plugins.
Built with 🧡 by Very Good Plugins.