MCP & AI reporting

How to Connect YouTube Analytics to Claude with MCP

Connect YouTube Analytics to Claude with the Data Bloo MCP and pull views, watch time, subscriber growth and revenue straight from the chat, no exports, no Studio tabs. It's read-only, so it's safe, and here's the 2-minute setup.

Free to start Read-only & secure Works in ~2 min
ClaudeData Bloo connected
Pull views, watch time and subscribers gained for my YouTube channel, last 30 days.
query_data · YouTube Analytics ✓
Here's your last 30 days on YouTube:
Metric
Value
Video views
842,317
Likes
61,204
Subscribers gained
4,812
That's a 4:21 average view duration, with views up 12% vs the prior period. Want a breakdown by video?
Reply to Claude…
The one thing you need

Your Data Bloo MCP URL

Paste this into Claude when you add a custom connector. Then expand Advanced settings and enter 43 in the OAuth Client ID field, leave the Client Secret blank. That's the whole secret; everything below is just where to click.

https://mcp.databloo.com/mcp
Using Claude Code instead? Grab the one-line CLI command →

What connecting YouTube Analytics to Claude actually means

You can ask Claude about your YouTube channel and get a real answer, pulled from your actual account, in seconds. Type "how did my videos do last month" and Claude reads your numbers and tells you, no screenshots from the app, no dashboard to open. The connection runs through the Data Bloo MCP over YouTube's official Analytics and Data APIs, takes about two minutes to set up, and it's read-only, so Claude can analyze your content but can never post, reply or change anything.

Want Claude to publish videos from a chat, or dig through public YouTube trends and other creators' channels? That's the territory of community MCP servers, self-hosted, on your own Google Cloud credentials. Want Claude to read, analyze and report on your own YouTube Analytics, blend it with Instagram, TikTok and your ad channels, and feed the same data to your Data Studio dashboards? That's Data Bloo, and that's what the rest of this guide covers.

Why connect YouTube Analytics to Claude

Stop exporting YouTube Studio reports. Start asking.

The same YouTube channel you already trust for your Data Studio reports, now answering questions in a chat. No app-hopping, no dashboards to open.

Ask, get instant answers

"Which videos got the most watch time last week?" Claude pulls the numbers and explains them.

Reports inside the chat

Ask for a 30-day YouTube view and get tables plus a summary ready to share, no Data Studio setup.

Client-ready summaries

"Turn the last 30 days of YouTube into an executive summary." Paste it into Slack, email or a doc.

Spot what's working

"Why did views spike on Tuesday?" Claude looks across videos, dates and audience data and explains it.

Blend beyond YouTube

Line YouTube up against Instagram Insights, TikTok Insights or your Google Ads spend in one answer.

Connect once, use everywhere

The same YouTube channel you linked for Data Studio is instantly available to Claude, zero duplicate setup.

Supported data sources

YouTube Analytics, plus every other connector

Already connected in Data Bloo? It's instantly available to Claude, connect once, use everywhere.

Pick your route

Three ways to connect YouTube Analytics to Claude

There are three real options, built for different people. Here's the honest version, including the case where the answer isn't us, so you pick the right one the first time.

Recommended for reporting

A connector like Data Bloo

Connect once, over YouTube's official APIs, and your channel analytics, plus every other source in Data Bloo, are available to Claude any time. Read-only, blends across channels, and the same connection feeds your Data Studio reports.

A community MCP server

Google publishes no official YouTube MCP. What exists are unofficial GitHub servers: most read public data by scraping, or post content, and all need API keys and self-hosting.

A manual export

Download a report from YouTube Studio, save the file, upload it to Claude. Free, and it works once. Then you do it again next week, separately for every channel.

Data Bloo vs a community MCP vs a manual export

Data Bloo
Community MCP
Manual export
Setup
~2 min, point & click
Clone a repo, API keys, self-host
New export each time
Reads your insights
Yes, official API
Mostly public data only
A snapshot
Changes your account
No (read-only)
Some can post content
No
Blends other channels
Yes
No, YouTube only
By hand
Feeds Data Studio
Yes, same connection
No
No
Works with other AI
Yes (ChatGPT, Gemini…)
Depends on the server
Any (paste a file)
Price
Free to start
Free code, your hosting
Free
Upkeep
None
Breaks when the API changes
Redo it each time

The bottom line: if you want Claude to research public YouTube or post content, a community server does that, at your own risk. If you want Claude to read and report on your own channel, across YouTube and everything else, and feed the same data to your dashboards, that's Data Bloo.

The honest bit

When a community MCP or native export is enough

Data Bloo isn't the right tool for every YouTube job. If you want Claude to research public YouTube, competitor channels, trending formats, other creators' videos, that's what community MCP servers built on the public Data API do, and an analytics connector can't, because your channel's Analytics API only sees your own data. If you want Claude to publish videos from a chat, community servers built on the Data API's upload endpoints exist too. And for a quick one-off look at last week's numbers, YouTube Studio's own export is free and instant.

The trade-offs are real. Community servers are unofficial: you clone a repo, manage API keys and hosting yourself, on your own Google Cloud project, with your own OAuth client and three scopes to approve. None of them blend YouTube with your other channels or feed a dashboard, and when Google changes the API you are the one who fixes it. For the channel you actually run, reading, blending and reporting on your own analytics, Data Bloo's official-API, read-only route is the lower-effort everyday pick. Plenty of teams run both: a research tool to study the competition, Data Bloo to report.

Before you start

What you need

Three things, and you probably already have them.

A Data Bloo account with YouTube Analytics connected. Your channel needs to be a Business or Brand account you own, that's what unlocks the Analytics API. If you already use Data Bloo for your Data Studio reports, your source is ready.
A Claude account. Desktop, Web or Claude Code all work, and a free Claude account is enough to start.
Pop-ups allowed for sign-in. Data Bloo's sign-in opens a browser window during setup, so make sure your browser isn't blocking it.
Setup · ~2 minutes

How to connect YouTube Analytics to Claude

Pick your Claude client. Desktop & Web are easiest for most marketers; Claude Code is a one-liner for developers.

1
Open Claude and click the + in the chat

Launch Claude Desktop or claude.ai. In the chat input, click the + icon on the left to open the tools menu.

2
Go to Connectors → Manage connectors

Hover over Connectors, then click Manage connectors to open your connector settings.

3
Click + → Add custom connector

Click the small + at the top of the connector list, then choose Add custom connector.

4
Name your connector "Data Bloo"

Type Data Bloo in the Name field. That's how you'll find it inside any conversation later.

5
Paste the Data Bloo MCP URL

In the Remote MCP server URL field, paste https://mcp.databloo.com/mcp. Then expand Advanced settings and enter 43 in the OAuth Client ID field, leave the Client Secret blank.

6
Click Add and sign in

Claude opens your browser on Data Bloo's sign-in page, sign in and approve so Claude can read your data. You sign in once.

7
Ask about your channel

Start a new chat and try: "Using Data Bloo, pull views, watch time and subscribers gained for my YouTube channel for the last 30 days." Claude returns a table plus a short analysis.

Step 1, Register the Data Bloo MCP

Open your terminal and run:

terminal
# Register Data Bloo as an HTTP MCP server in Claude Code
claude mcp add --transport http databloo https://mcp.databloo.com/mcp
Step 2, Authenticate with Data Bloo

Next time you start a Claude Code session, Claude opens your browser to sign in to Data Bloo. Sign in once, the connection persists across sessions.

Step 3, Verify

Run /mcp, you should see databloo with status connected.

Confirm it works: in a fresh chat, ask "Using Data Bloo, list all the YouTube channels I have connected." If Claude returns your accounts, you're fully connected.

See it in action

Take the MCP for a spin

Walk through connecting YouTube Analytics to Claude and pulling a report, no signup, right here in the page.

Under the hood

Seven read-only tools, why this can't get you banned

You just ask in plain language, Claude picks the right tool. The typical flow: list_data_sources → get_connector_accounts → list_fields → query_data.

Tool
What it does
get_user
Your plan, MCP access, usage limits and remaining calls.
list_data_sources
Every available connector, with its name and description.
get_connector_accounts
Your linked YouTube channels, and the IDs to query.
list_fields
The valid metrics and dimensions for YouTube Analytics.
query_data
The actual pull: metrics and dimensions over a date range.
list_accounts
Every connected account across every connector, in one call.
get_dates
Turns "last month" into the exact start and end dates to query.

Read-only, always. Claude can pull and analyze your YouTube Analytics, it can never publish a video, edit a title, reply to a comment or change any channel setting. Nothing YouTube could ever flag.

Why Data Bloo

Read-only safety and your dashboards, in one connection

The unofficial tools make you choose: hand an AI a scraper that might cross YouTube's terms, or keep exporting from Studio. Data Bloo doesn't ask you to choose. It reads over the official API, it reports, and the exact same connection already powering your Data Studio dashboards now answers questions in Claude.

It can't touch your account

All seven tools are read-only, and every call goes through YouTube's official APIs. Claude pulls and analyzes your insights, but it can't post a video, reply to a comment or change a setting, so there's no wrong instruction that could put your account at risk. No safety checklist to memorize, because there's nothing to switch off.

One connection, two surfaces

The YouTube Analytics source you built for Data Studio is the same one Claude reads. No second setup, no second bill, and the numbers Claude quotes always match the dashboards you send clients. It's the one thing a self-hosted, YouTube-only script structurally can't give you.

The data

What YouTube Analytics data you can pull

The same metrics you use in your reports, sliced by video, date, traffic source, country, device and age group.

Views & watch time

Video views, Engaged views, Estimated minutes watched, Average view duration (sec) and Average view duration percentage, per video or across the channel.

Engagement & subscribers

Likes, Dislikes, Comments, Shares, Gained subscribers and Lost subscribers, plus Card impressions, Card clicks and Card click rate.

Breakdowns

Video title, Traffic source type, Country, Device type, Operating system, YouTube product, Age group and Gender, so you can rank content or trace where views come from.

Revenue, if you monetise

Estimated revenue, Gross revenue, CPM, Playback based CPM, Ad impressions, Monetized playbacks and YouTube Premium views, once the monetary scope is granted at connect time.

Real answers

What Claude actually gives you back

Three real prompts and the kind of answer Claude returns once YouTube Analytics is connected through Data Bloo, numbers, then a plain-language read.

"Pull views, watch time and subscribers gained for my YouTube channel, last 30 days."

Claude: Last 30 days on YouTube, 842,317 views, 61,204 estimated minutes watched and 4,812 subscribers gained. Average view duration is 4:21, or 38% of each video, with views up 12% on the prior period.

The read: engagement is climbing faster than views, your content is holding attention, not just collecting clicks.
"Which videos got the most views in the last 14 days?"

Claude: Top video, Behind the scenes: packing week at 214,900 views and 11.2% engagement. Second, 3 mistakes new sellers make at 132,400 views. Your talking-head explainers average roughly double the engagement of your product clips.

The read: the format is out-earning the polish, plan more explainers before investing in another produced clip.
"Break down last month's views by country."

Claude: United States 38%, United Kingdom 14%, Germany 9%, with the rest spread across 40+ countries. Watch time from the US grew 21% month over month.

The read: the US is your growth engine right now, worth timing posts to US evening hours and testing US-specific hooks.

Example outputs shown for illustration; your figures come live from your own connected account.

Data Bloo MCP

Not just charts. Finished, branded deliverables

Plug your live YouTube data into Claude, ChatGPT or Gemini through our MCP, and generate branded presentations, audits and executive reports straight from a chat prompt.

Client presentations

Slide-ready decks with your logo, colors and commentary, built from live data, ready to send.

92
!

Audits

Automated account audits that flag issues, wins and opportunities, with clear next steps.

VIEWS
842K
ENG
8.1%
FOL
+4.8K

Executive reports

Concise, narrative summaries for leadership, the numbers that matter, explained in plain language.

Try it

Prompts to paste into Claude

Once connected, drop any of these into a fresh chat. Name Data Bloo in your first message, then drill in.

Discovery
"Using Data Bloo, list all the YouTube channels I have connected."
"What fields and date ranges can I pull for my YouTube channel?"
Pulling data
"Pull views, watch time and subscribers gained for my YouTube channel, last 30 days."
"Show me views and estimated minutes watched week by week for last month."
Breakdowns
"Break down last month's views by traffic source type and device type."
"Show my audience split by gender for the last 30 days."
Reporting & analysis
"Write a client-ready summary of my channel for October, with three takeaways."
"Compare this month's average view duration percentage to last month's and tell me what changed."
Top content
"Rank my videos by views for the last 14 days and show average view duration next to each."
"Which videos drove the most shares this month, and what do they have in common?"
Subscriber growth
"Chart my subscribers gained and lost day by day for the last 60 days."
"Which days gained the most subscribers last month, and what did we publish?"
Cross-channel
"Compare YouTube watch time against Instagram Insights and TikTok Insights this month."
"Line up YouTube views against my Google Ads spend for the last 30 days."
Audience
"Where is my audience? Break views down by country, biggest first."
"How does my audience split by gender, and has it shifted this quarter?"
Who it's for

Built for how you actually work

Same connection, different job to be done. Here's the prompt each type of marketer tends to start with.

Agencies

Pull and compare across every client's channel without switching logins, then draft the monthly report in the chat.

"Compare average view duration and subscriber growth across all my connected YouTube channels this month."

Content & social teams

Learn which formats, hooks and posting days actually work, from your own numbers, not guesswork, and plan next month's calendar on evidence.

"Rank last month's videos by average view duration percentage and tell me what the top five have in common."

Creators & brands

Track your own growth without living in the analytics tab, and turn a quarter of posting into a clean story for sponsors and partners.

"Summarize my channel growth this quarter, views, watch time and subscribers, in plain language."
Troubleshooting

Common issues and fixes

Claude says it can't see your accounts

You're likely not signed in yet, or YouTube Analytics isn't connected in Data Bloo. Ask "Using Data Bloo, list the accounts I have connected." If it comes back empty, open Data Bloo, confirm your YouTube Analytics source is connected, then try again. Remember the channel must be one you own or manage, and revenue fields need the monetary scope approved at connect time.

The numbers don't match YouTube Studio exactly

Small gaps are normal. YouTube finalises some metrics on a 24-72 hour delay, revenue later still, your channel time zone shifts which day a view lands in, and Studio rounds big numbers. For trends, comparisons and reporting the Data Bloo pull is solid; for a video you posted an hour ago, Studio is freshest.

A breakdown query comes back empty

That is usually a field-combination rule, not a bug. Age group and Gender only return alongside Viewer percentage, and the retention fields need a single-video filter. Channel total page views, subscribers and video count are all-time figures from the Data API, so they never split by date. Ask Claude for one of those groups on its own.

Claude won't take an action on your account

That's on purpose. The connection is read-only. If you want to publish videos or reply to comments from a chat, that's an unofficial content-posting MCP, not this.

Good to know

Query notes & FAQs

One breakdown dimension per call. For multiple breakdowns, ask Claude to run separate queries and combine them after.
Confirm fields first. Field IDs vary per connector. Claude usually lists fields before querying to avoid rejected requests.
!Some fields only pair with each other. Age group and Gender only return with Viewer percentage, and the retention fields need a single-video filter.
Numbers vs YouTube Studio. Small gaps are normal, a 24-48 hour processing delay, time zones and in-app rounding.

Add a custom connector in Claude, name it Data Bloo, and paste the MCP URL https://mcp.databloo.com/mcp. Sign in once, then ask Claude about your channel in plain language.

No. Google has released MCP servers for a number of its own products, but YouTube is not among them. Every YouTube MCP you will find is a community project: unofficial, self-hosted, and running on a Google Cloud project and OAuth client you create yourself. Data Bloo reads your own channel over YouTube's official Analytics and Data APIs, read-only and hosted.

It's free to start, no credit card. The free tier includes MCP access with usage limits; paid plans raise the limits and add more connected accounts.

Three read-only scopes: yt-analytics.readonly for the reports, youtube.readonly for video and channel metadata like titles and thumbnails, and yt-analytics-monetary.readonly if you want revenue. All three are read scopes, none of them can change your channel.

No. All seven MCP tools are strictly read-only. Claude can pull and analyze your data but can never post a video, reply to a comment or change any account setting.

YouTube keeps channel history from the day the channel started, so the Analytics API can reach a long way back, subject to the ranges YouTube allows for each report type. Revenue history is available only for periods you were monetised, and only once the monetary scope is granted.

Any MCP-compatible client, Claude Desktop, Web and Code, plus ChatGPT, and Gemini. The same URL works across all of them.

Yes. As long as they're connected in Data Bloo, ask Claude to compare YouTube against Instagram Insights, TikTok Insights, your Google Ads spend or Google Analytics 4, and it pulls one blended answer.

No. A free Claude account is enough to add the Data Bloo connector and start pulling YouTube reports. Your Claude plan is separate from Data Bloo, and the connector works on Claude Desktop, Web and Code.

Yes. You sign in once through Data Bloo's secure OAuth flow, every call runs over YouTube's official APIs, and the connection is strictly read-only. No scraping, no password sharing, and no action YouTube could flag.

Yes. Ask Claude to list your connected YouTube channels, and it can pull and compare across them, handy for agencies running multiple clients.

Yes. Pair the MCP with Claude's scheduled tasks or Claude Code for an automatic Monday-morning content digest, subscriber-growth alerts or a recurring client update, unattended.

Simple, transparent pricing

Scale your reporting without limits

Every plan includes all data sources. Start free, upgrade only when your dashboards demand it.

FREE
$0/ forever

Best for individuals or early-stage teams starting with marketing data.

Create free account
Destinations included
& more
1 account per connector300 daily refreshes (API calls)All data sources includedData Bloo MCP
STARTER
$8.33/mo
billed annually · save $20/yrAnnual plan only

For individuals who need unlimited refreshes with a single account.

Choose Starter
Destinations included
& more
1 account per connectorUnlimited daily refreshesAll data sources includedData Bloo MCPEmail support
Most popularPRO
$16.66$19.99/mo
billed annually · save $40/yrbilled monthly

For freelancers & growing teams that need more accounts and volume.

Choose Pro
Destinations included
& more
Up to 5 accounts per connectorUnlimited daily refreshesAll data sources includedData Bloo MCPEmail support
AGENCY
$33.33$39.99/mo
billed annually · save $80/yrbilled monthly

For agencies managing multi-client reporting at scale.

Choose Agency
Destinations included
& more
Unlimited accounts per connectorUnlimited daily refreshesAll data sources includedData Bloo MCPPriority email & chat support

No credit card required to start · Cancel anytime · See plan FAQs →

Chat with your YouTube channel today

Connect YouTube Analytics to Claude in under 2 minutes and pull reports straight from the chat. Free to start, no credit card.