Youtube Organic Mcp

io.github.lanternrowPublished by GitHub account lanternrowv1.0.0Updated Oct 24, 2026

YouTube organic analytics — channel stats, video performance, watch time & audience insights.

VerifiedSTDIODesktop onlyData & AnalyticsBusiness & Commerce

Overview

AI-generated overview

A local MCP server that gives an assistant read-only access to your own YouTube channel's organic analytics via the YouTube Data and Analytics APIs.

What you can do
List configured channels and the default account, including multi-account setups with an optional account parameter on every tool. Retrieve channel profile and lifetime stats such as subscribers, total views, video count and uploads playlist. Page through uploads with per-video views, likes, comments and duration, and fetch details for specific video IDs in batches. Pull channel analytics over a date range: views, watch time, average view duration and percentage, subscribers gained and lost, likes, comments and shares, optionally broken down by day. Pull the same metrics for a single video over a date range.
When to use it
Useful when you want an assistant to review your own channel's performance, compare videos, or trace day-by-day trends in views, watch time and subscriber changes without exporting reports by hand. Suited to channel owners and agencies already using Google OAuth tooling.
Requirements
Runs locally as a Node.js process (Node 18 or later) started from the npm package. Requires a Google Cloud project with the YouTube Data API v3 and YouTube Analytics API enabled, an OAuth desktop-app client, and a refresh token for the channel owner. Credentials are supplied through the environment variables YOUTUBE_CLIENT_ID, YOUTUBE_CLIENT_SECRET and YOUTUBE_REFRESH_TOKEN, or YOUTUBE_ACCOUNTS for multiple channels. A helper script needs Python with google-auth-oauthlib to obtain the token.
Before you install
The server needs a Google OAuth client secret and a long-lived refresh token, which grant ongoing access to your channel's data; store them in configuration rather than sharing them. The token helper writes credentials to a local account file. Access is described as read-only, but the refresh token itself is a durable credential that should be revoked if exposed. Data is sent to Google's APIs, and the server is desktop-only, so it cannot run in a web context.

Installation

In SourceWeft

  1. Open Youtube Organic Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

youtube-organic-mcp

MCP server for YouTube organic analytics — channel stats, video performance, watch time, and audience engagement via the YouTube Data API v3 and YouTube Analytics API v2.

Built for Claude Code and any MCP-compatible AI tool. Gives your AI assistant direct, read-only access to your own channel's organic data — subscribers, views, watch time, per-video engagement, and day-by-day trends.

Part of The SEO Engine toolkit by Rex Jones — AI-powered SEO and social media tooling for agencies and businesses.

Why this exists

  • No good open-source YouTube organic MCP existed. Plenty of ad MCPs; organic channel analytics, nobody.
  • YouTube has the richest organic API of the major platforms. Watch time, average view duration, subscribers gained/lost, traffic sources — none of it gated behind a multi-week review.
  • Reuses your existing Google OAuth. If you already run the GA4 / GSC / Google Ads MCPs, the same OAuth client works here.

Tools

ToolDescription
list_accountsList configured channels and the default
get_channel_infoChannel profile + lifetime stats (subscribers, total views, video count, uploads playlist)
get_videosPaginated uploads with per-video views, likes, comments, duration
get_video_detailsDetails for specific video IDs (batch up to 50)
get_channel_analyticsChannel analytics over a date range: views, watch time, avg view duration/%, subs gained/lost, likes, comments, shares — optionally by day
get_video_analyticsThe same metrics for a single video over a date range

All tools accept an optional account parameter for multi-account setups.

Getting connected

Step 1: Enable the APIs

In Google Cloud Console (any project — you can reuse an existing one), enable YouTube Data API v3 and YouTube Analytics API.

Step 2: Get a refresh token

Create an OAuth client of type Desktop app and download its client_secret JSON. Then run the helper (needs pip install google-auth-oauthlib):

bash
python3 scripts/get_youtube_token.py /path/to/client_secret.json my-channel

Authorize with the Google account that owns the channel (pick the Brand Account if prompted). It prints the three YOUTUBE_* values to drop into your config and writes them to .youtube_account.json (gitignored).

Step 3: Configure

Add to your Claude Code MCP settings:

json
{  "mcpServers": {    "youtube-organic": {      "command": "node",      "args": ["/path/to/youtube-organic-mcp/dist/index.js"],      "env": {        "YOUTUBE_CLIENT_ID": "your_client_id.apps.googleusercontent.com",        "YOUTUBE_CLIENT_SECRET": "your_client_secret",        "YOUTUBE_REFRESH_TOKEN": "1//your_refresh_token"      }    }  }}

Or set YOUTUBE_ACCOUNTS to a JSON array for multiple channels (see .env.example).

Architecture

src/  index.ts          # MCP server entry point, tool registration  accounts.ts       # Multi-account resolution (client_id/secret/refresh_token)  client.ts         # OAuth token minting + Data/Analytics API HTTP client  types.ts          # TypeScript interfaces for API responses  tools/    channel.ts      # get_channel_info + uploads-playlist resolver    videos.ts       # get_videos, get_video_details    analytics.ts    # get_channel_analytics, get_video_analytics
  • Zero external HTTP dependencies — native fetch (Node 18+)
  • Auto-refreshing auth — access tokens minted from the refresh token, cached per process
  • Multi-account support — monitor multiple channels from one server

License

MIT

Source: README.md at commit d3447fa

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.