MCP Rules Everything Around Me

I connect Claude to basically everything at beehiiv. The one gap that always bugged me: meeting context.

Granola fixes that. Granola just shipped an MCP integration that pipes your meeting notes directly into Claude, ChatGPT, or whatever AI tool you’re using.

No more copy-pasting transcripts into Claude. Just ask for:

Teams at Notion, Figma, and Y Combinator already run on Granola.

I've been writing this newsletter for two years. Nothing has changed how I operate it more than the last six weeks.

That's when we launched the beehiiv MCP.

MCP (short for Model Context Protocol) is an open standard that lets AI models like Claude connect to external tools and data sources (like Slack, Google Drive, and now beehiiv).

For example, I asked Claude to give me a breakdown of who’s reading my newsletter: age, gender, professional profile, the types of companies they work for, industries, household income, location, and more.

It took me 10 seconds to ask in plain English, and the results I got were pretty damn impressive:

It would have taken an intern an entire week to compile and analyze that. Which is why it’s the perfect job for the MCP: it requires context, reasoning, and the ability to connect dots across your entire dataset.

I’m not alone. Every day, thousands of creators use our MCP to do things that were previously too time-consuming or outright impossible.

A few weeks ago, we made it available to all users (including those on the free plan). The world is changing — more people are shifting their work to be done in AI clients like Claude and ChatGPT.

Rather than fighting it, we’re leaning all the way in.

We’re building the underlying infrastructure for anyone with an audience, whether that work is being done in the beehiiv platform, through an AI client, or whatever interface comes next.

I used to spend 4+ hours a week on newsletter ops — now it’s a few minutes. Here are the 5 workflows that got me there…

This is probably the most generic use case, but one of the most helpful.

I used Claude to analyze every newsletter I've ever sent and create a style guide based on my voice and tone. Now, I submit a rough draft and it will fact-check every claim via web search, fix flow and grammar, and return a publish-ready version with corrections and suggested changes clearly outlined.

Everyone’s writing would be a whole lot better with a dedicated editor, and thanks to the beehiiv MCP and AI, everyone can have one trained on their entire archive of content.

I once again had Claude analyze every newsletter I’ve ever sent, this time to assess the correlation between subject lines and open rates.

It extracted clear patterns, backed by data, and uncover those that consistently outperformed:

And those that underperformed:

Based on its findings, Claude built a framework called CREAM — five patterns that consistently outperform my average open rate by 3-5%.

Now I pass my final draft to Claude and it returns subject lines based on the framework and real data.

My newsletter generates revenue from sponsors.

I had Claude analyze the correlation between ad copy and open rates for all of my previous newsletters. It found a clear pattern: certain promotional phrases (like "free" or "use promo code X") were hurting my delivery rates.

It also confirmed what I already suspected — ads written in my own voice almost always outperform generic ad creative from the brand.

Now, I simply pass a draft of the ad to Claude and it’ll return a more polished version, consistent with my voice and tone, and run everything through a custom deliverability filter to avoid spam-trigger language.

The outcome: less spam filtering and promotions, higher open rates, better performing ads, happier repeat advertisers.

Every week, I owe my sponsors a report on how their ad performed.

This used to take 20-minutes to click through the beehiiv dashboards, manually tally the impressions, clicks, and CTR, then package it up with some analysis.

That was life before the beehiiv MCP. Now?

Every Tuesday, Claude automatically pulls the previous week's newsletter from beehiiv, identifies the sponsored ad placement, and generates a polished PDF performance report.

It even fetches the advertiser's logo and formats everything in BDE's Windows 98 aesthetic. The whole thing runs without any manual input.

Sponsors are the lifeblood of my newsletter — they pay the bills. Securing new sponsors is the name of the game to scale advertising revenue.

Rather than doing cold outreach, it’s much easier to pitch people who are already familiar with Big Desk Energy. So I built an AI Lead Gen tool to help secure new sponsorships:

This runs automatically every single day. Claude is delivering me warm leads without me ever lifting a finger.

The truth is — I'm barely scratching the surface of what's possible with the beehiiv MCP. Every time I log onto X, I see more users posting workflows and automations that I haven't even thought of yet.

What have you built? Reply with your best examples and I'll feature them in an upcoming post.

If you enjoyed this post or know someone who may find it useful, please share it with them and encourage them to subscribe: mail.bigdeskenergy.com/p/mcp-rules-everything-around-me

Desert nights in the lab 🌵. Send me the best AI generated home office you can come up with (I’m running out of prompts).

Think you can generate a better office? Reply with your submissions 📨.

Some of my favorite content I found on the internet this week…

Chat with DenkBot — my AI clone. It’s trained on everything I’ve ever published and the entire beehiiv knowledge base 🧠.

Or you can book an hour session with me (real me) directly → here.

Turn on, tune in, drop out. Click on any of the tracks below to get in a groove — each selected from the full Big Desk Energy playlist.

Share this newsletter with your friends, or use it as a pickup line.

👉 Your current referral count: {{ rp_num_referrals }} 👈

Or share your personal link with others: {{rp_refer_url_no_params}}

📥 Want to advertise in Big Desk Energy? Learn More