YouTube MCP: channel analytics in 
Claude & 
ChatGPTPorter Metrics connects your YouTube channel’s analytics to Claude, ChatGPT and other AI clients through one MCP server. MCP is the Model Context Protocol, the open standard AI apps use to reach other tools. Ask which videos grew watch time, where viewers found you or how Shorts compare with long videos, and the answer comes from your channel.
Every metric and dimension Porter reads is in the YouTube fields list.
One server, every channel you manage: Porter connects YouTube to the AI clients, fields and workflows marketing teams already use. The same Porter server URL works in Claude, ChatGPT and any MCP client that supports remote servers. Porter reads Google’s YouTube Analytics API with your Google sign-in, so you never create a Cloud project or paste a key.
Works in: Claude (Claude.ai, Claude Desktop, Cowork and Claude Code), ChatGPT, Cursor and any MCP client that supports remote servers.
Channel and video: Channel Name · Channel ID · Video Title · Video ID · Video URL · Video Published Date · Video Duration (s) · Video Thumbnail URL · Content Type
Views: Views · YouTube Premium Views · Views by Country
Watch time: Estimated Minutes Watched · Average View Duration (s) · Average Percentage Viewed · YouTube Premium Minutes Watched · Minutes Watched by Country
Subscribers: Subscribers Gained · Subscribers Lost · Subscribers (Total) · Subscribers Gained by Country
Engagement: Likes · Dislikes · Comments · Shares · Videos Added to Playlists · Videos Removed from Playlists
Porter has 34 ready-made YouTube fields, 18 metrics and 16 dimensions. Each one is in the full YouTube field reference.
Discovery: Traffic Source · Playback Location · Subscribed Status
Device and place: Device Type · Operating System · Country
Time: Date · Video Published Date
Send work from Claude or ChatGPT to: email on a schedule
Turn answers into: live dashboards · client reports · weekly summaries
Same channel in other tools: all MCP connectors
YouTube finalizes each day’s numbers after a short delay, so the last two or three days fill in later. Country rows cover the whole date range, not single days, and countries under YouTube’s privacy threshold don’t appear.
Porter’s YouTube MCP signs in with Google and reports on your channel without changing it. Claude reads views, watch time, subscribers and traffic sources while videos, titles, playlists and comments stay exactly as you set them. You can disconnect Porter whenever you like.
Every YouTube question is a report. Uploads, title edits, playlists and comment replies stay in YouTube Studio, where you handle them as usual.
Google gives each project 10,000 YouTube Data API units a day. Porter runs the project and the sign-in, so you never request quota.
Reporting is billed per connected YouTube channel. One more question about the same channel adds nothing to the bill.
Disconnect YouTube in Porter, or remove Porter from your Google account permissions, and access ends. Connect again later whenever you like.
Porter’s YouTube MCP uses one server URL in every AI client, plus a Google sign-in you complete once. Claude takes Porter as a plugin or a custom connector. ChatGPT takes it through the Porter Metrics app or developer mode. Both read the same YouTube channels, with the same fields.
Use the Claude plugin for the guided setup. Claude keeps the Porter plugin synced when new tools ship.
portermetrics/porter.portermetrics/porter.Anthropic’s guide to custom connectors using remote MCP walks through the same path, and custom connectors work on Free plans with a limit of one. The Claude-specific setup and use cases live on the YouTube connector for Claude page.
Click-by-click YouTube to Claude demo:
Use manual setup when Claude asks for a custom connector instead of a plugin.
Porter.https://mcp.portermetrics.com/mcp.Use the Porter Metrics app for the fastest ChatGPT route.
OpenAI documents connected apps in ChatGPT and custom MCP servers in ChatGPT developer mode.
Click-by-click YouTube to ChatGPT demo:
Use developer mode when you want the full Porter setup in ChatGPT: connector plus skill.
Porter Metrics.https://mcp.portermetrics.com/mcp as the MCP Server URL.https://mcp.portermetrics.com/skill.zip.skill.zip to your ChatGPT project.Google hasn’t published its own YouTube MCP server as of November 2026. What Google offers is the YouTube Data API and the YouTube Analytics API, which every YouTube MCP server builds on, plus Ask Studio inside YouTube Studio. Use Porter’s URL above for a hosted server you sign into with Google, next to your other channels.
Try this one once you’re connected:
Each YouTube skill in Porter’s MCP is a ready-made prompt for one question a channel team asks every week. A skill turns live channel data into a top-videos list, a traffic source check, a cross-channel answer or a scheduled email. Copy a prompt into Claude or ChatGPT, then change the dates, channels or thresholds to fit yours.
The research skills blend YouTube with your social and analytics accounts, so connect Instagram, Facebook or GA4 in Porter first.
These run on a schedule and send what they find, while your channel stays as it is.
Marketers who report on YouTube next to the rest of their channels get the most from Porter’s MCP. Social media managers, agencies, content marketers and analysts use it to turn a channel question into a top-videos list, a traffic source check or a weekly report in one chat.
For marketers who report on YouTube next to their other channels.
Your boss isn’t asking about one video. They’re asking whether YouTube is worth the editing hours.
You want to read any public video’s transcript, search YouTube or study a competitor’s channel. A transcript or search server covers that job, and you can run it next to Porter.
“YouTube MCP” names a few different setups, and Google itself hasn’t published one as of November 2026. Most servers read public videos: transcripts, search results and comments. Porter covers your own channel’s analytics from one hosted server, plus dashboards and scheduled emails.
A transcript server hands your AI what a video says. Porter’s MCP hands it how your channel performs, next to everything else you run.
Both use Google’s YouTube APIs. Here is where they part.
| Porter | Your own server on Google’s YouTube APIs | |
|---|---|---|
| Same job, different reach | ||
| Server | Hosted by Porter at mcp.portermetrics.com/mcp | You host it on your machine or server |
| Sign-in | Google login | A Google Cloud project, API key or OAuth client you manage |
| Channel analytics | 34 named fields: views, watch time, subscribers, traffic sources, countries | The YouTube Analytics metrics you code for |
| Channel changes | None; reports only, and you edit videos in YouTube Studio as usual | Whatever you build with the Data API |
| Quota | Porter’s project and sign-in | Your project’s 10,000 units a day |
| Works in | Claude, ChatGPT, Cursor and any remote MCP client | The clients you configure it for |
| Price | Included in every Porter plan, the free plan too | Free to build; you maintain it |
| Only one side | ||
| Instagram, Facebook and GA4 in the same answer | Yes, from Porter’s 30+ data sources | — |
| Live dashboards at their own link | Yes | — |
| Scheduled reports by email | Yes | — |
| Skills: whole YouTube tasks, already written | Yes | — |
The right column follows Google’s YouTube Analytics API and Data API docs (as of November 2026).
Build your own if you need public-video data or tools Porter doesn’t cover and have time to maintain it. Porter’s rows under Only one side are what happens when YouTube is one channel among several.
Most servers called “YouTube MCP” fetch transcripts and search public videos. They answer what a video says, not how your channel performed.
Porter’s YouTube MCP reads your channel, not your ad accounts. YouTube ad spend, views and conversions come from Google Ads, so ask through the Google Ads MCP on the same server. Programmatic YouTube buys show up in Display & Video 360.
Plenty of them rank for this search, and they split three ways.
Porter reads your channel next to your marketing from one hosted server, starting on the free plan.
Every Porter plan includes the YouTube MCP at no extra cost, the free-forever plan too. Porter bills Reporting per connected data source account, and each YouTube channel counts as one. Channel questions are reads, so they use no automation credits. Full details are on Porter pricing.
| What you use | What you pay | What is included |
|---|---|---|
| YouTube MCP | Included in every plan | The server URL, Claude and ChatGPT setup, reports, skills and scheduled emails |
| Reporting | From $12.50/mo per data source account, billed annually | Reports and dashboards across YouTube and your other sources. The free plan keeps unlimited connected accounts, up to 30 days of history and 15 days in AI chats |
| Automation | By credits | Approved changes on your other sources, such as pausing a Google Ads campaign. The free plan includes 100 credits a month |
Free means usable: the free plan connects unlimited YouTube channels, keeps up to 30 days of history and gives you 100 credits a month.
Google hasn’t published its own YouTube MCP server as of November 2026. Google offers the YouTube Data API and the YouTube Analytics API, and every YouTube MCP builds on them. Porter’s YouTube MCP runs at https://mcp.portermetrics.com/mcp, signs in with Google and puts your channel next to your other channels.
Porter’s YouTube MCP server URL is https://mcp.portermetrics.com/mcp. Paste it into Claude, ChatGPT or another AI client as a custom connector, then sign in with the Google account that manages your channel. The same URL also reaches your Instagram, Facebook and GA4 accounts in Porter.
Porter’s YouTube MCP is included in every Porter plan, the free-forever plan too. The free plan covers unlimited connected accounts, up to 30 days of history, 15 days in AI chats and 100 automation credits a month. Paid Reporting starts at $12.50 a month per data source account, billed annually, and the 14-day trial needs no card.
No. You sign in with the Google account that owns or manages the channel, and Porter handles the API project and quota. A self-built server usually asks you to create a Google Cloud project and an API key or OAuth client before it reads anything.
Yes. Connect each channel you manage, and Claude compares them in one answer with Channel Name as a column. Reporting is billed per connected channel, and the free plan connects unlimited accounts.
Porter reads your channel’s analytics: views, watch time, subscribers and traffic sources. Transcripts of public videos are a job for a transcript MCP server, and you can run one next to Porter in the same Claude account.
Install the Porter plugin from Claude Settings → Customize → Plugins. Add the portermetrics/porter marketplace, install Porter Metrics from the Directory and sign in with Google when the connector asks. Then ask Claude for your YouTube channels.
MCP is the Model Context Protocol, an open-source standard for connecting AI applications to external systems like YouTube. MCP isn’t the agent. Claude and ChatGPT are the agents, and Porter’s MCP is how they reach your YouTube channel.
Check the dates first. YouTube fills in the last two or three days later, so recent totals still move. Breakdowns by device, traffic source or country can land slightly below the channel total, because YouTube leaves out rows under its privacy threshold.
YouTube reports country numbers for the whole date range only. Ask for Views by Country over the period, then ask a second question by Date for the trend. Claude lines the two answers up for you.
Connect YouTube to Claude or ChatGPT and start with top-video lists, watch time checks and dashboards that land in your inbox.
Start free: unlimited connected accounts on the free-forever plan, or a 14-day trial with everything unlimited and no card.