The Operator's Guide

Beehiiv MCP, the way an operator would actually use it.

Most creators ask Claude vague questions about their newsletter. Operators ask the ones that change what they ship next. Beehiiv shipped the bridge.

40 Prompts 6 Workflows 44 Tools Mapped
01 / Why this matters

Most newsletter software was built for teams of twelve. The MCP was built for you.

Beehiiv shipped an MCP connector that hooks your publication directly into Claude. Your account data becomes conversational. You stop clicking through dashboards and start asking questions.

It used to be built for marketing teams with a Salesforce admin and a data analyst on staff. You ended up with dashboards designed for someone else's job and a nagging feeling you should be doing more with your data than you actually are.

The MCP changes the shape of the work. Instead of clicking through tabs to find an answer, you ask. Instead of exporting CSVs to find a pattern, you describe what you're looking for. Instead of building a segment in a query builder, you say what you want and watch it happen. For solo operators that matters more than it does for big teams. Big teams have analysts. You have you, your time, and a product to ship. What used to be Friday afternoon is now ten minutes on a phone.

CMO Take

Most MCP guides recommend prompts that assume more capability than the connector actually has. "Save it as a draft" is a popular suggestion that doesn't work yet. This guide stays accurate. Honest beats flashy.

This guide gives you 40 prompts organized by what you're trying to figure out, six workflows that turn the MCP into a weekly operating rhythm, and a section on stacking Beehiiv with your other tools to compound the value. Setup takes five minutes. Start there.

02 / Setup

Five minutes. No code.

Step 1. Add the connector in Claude

Open Claude or Claude Desktop. Settings → Connectors → Add custom connector. Name it "beehiiv" and paste the URL: https://mcp.beehiiv.com/mcp

Step 2. Authorize Beehiiv

Claude redirects you to Beehiiv's OAuth page. Sign in, click Connect, then Grant Access on the consent screen.

Step 3. Set tool permissions

Back in Claude, set the read-only tools toggle to "Always allow" so you don't get prompted on every query. Keep approval on the write tools.

Step 4. Test the connection

Start a new chat and type: "Show me my Beehiiv publications." If it returns your list, you're live.

Once you're connected, the 40 prompts below work immediately. No paid plan gate. If you don't have a publication yet, start one and come back.

Try beehiiv →
03 / What you can actually do

Read everything. Now write segments.

v1 shipped read-only with 44 tools. v2 added segment creation, the first write capability. More is on the way. Here's the honest picture as of today.

Read access: pull anything in your account

Write access: create and update segments

Even with one write tool, the loop is worth more than read-only ever was. Pull the data, decide what to do, build the targeting. Three steps that used to be three tools, now one conversation.

04 / Mental model

The MCP is not Google. It's a sharp analyst.

The biggest mistake people make is treating the MCP like a search bar. They type two words and expect magic. Better model: you're talking to a sharp analyst who has never seen your data before. They can pull anything you ask for, but only if you tell them what you want.

Three rules that work

1. Be specific about the time window.

"Last 30 days" beats "recently." If you don't specify, you'll get the default window and miss the trend you were actually after.

2. Be specific about the cut.

"Group by acquisition source" beats "tell me about subscribers." The cut is where the insight lives.

3. Ask for the so-what.

"Tell me what to do about this" beats "show me the data." This is the unlock. The MCP pulls data, Claude interprets it. Don't stop at the table. Ask what it means and what to do next.

05 / The 40 prompts

40 prompts organized by what you're trying to figure out.

Run a few each day and you'll know your account better in a week than most operators know it after a year. Tap any prompt to copy.

APerformance analytics
01What were my top 5 posts by open rate in the last 90 days, and what do their subject lines have in common?Copy
02Which posts had the biggest gap between open rate and click rate? Show me the top 5 and tell me what might be causing the drop-off.Copy
03Show me my last 10 posts ranked by total unique email clicks. Then group them by content tag and tell me which tag drives the most clicks per send.Copy
04Compare my open rates and click rates over the last 4 weeks vs. the previous 4 weeks. What changed?Copy
05Which day of the week and time of day produces my best open rates? Show me the data, not just a recommendation.Copy
06Find the 3 posts with the highest unsubscribe rate in the last 6 months. Pull the subject lines and content. What pattern do you see?Copy
07Which posts had the most web views relative to email opens? Those are the ones being shared.Copy
08Show me my bounce rate trend over the last 12 months. Flag any spikes and tell me what posts they came from.Copy
09Pull a "greatest hits" roundup of my top 5 posts in the last 90 days. Format it as ready-to-paste copy I can use in an email or social post.Copy
BSubscriber intelligence
10How has my subscriber base grown month over month for the last 6 months? Show me net adds and churn separately.Copy
11Break down my acquisition sources for all-time vs. the last 30 days. What's growing, what's shrinking, and what's stale?Copy
12Which posts drove the most new subscribers? Cross-reference post publish dates with subscriber signup spikes.Copy
13Show me my churn rate over the last 90 days. Are there specific weeks where it spiked?Copy
14What percentage of my subscribers came from referrals vs. direct vs. social? Use my real data.Copy
15Pull subscribers who signed up in the last 30 days but haven't opened any emails. How many are there and what was their acquisition source?Copy
16Show me the geographic or referral pattern for my paid subscribers vs. free. Where are conversions actually happening?Copy
17Which survey or poll responses are showing the strongest churn signals? Cross-reference response patterns with subsequent unsubscribes.Copy
CContent audit
18List every post I've published in the last 6 months and the content tags applied. Flag any post that's missing tags or has inconsistent tagging.Copy
19Compare my scheduled send time vs. actual published time for the last 12 posts. Am I drifting off cadence?Copy
20What topics have I covered most in the last 90 days? Group my post titles by theme and tell me what I'm overweighting.Copy
21Pull the full content of my last 3 best-performing posts and tell me what structural elements they share (hooks, length, formatting, CTAs).Copy
22Find posts that performed below my average open rate. Read the subject lines and content. What's the failure pattern?Copy
DAutomation diagnostics
23Show me the step-by-step performance of my welcome sequence. Where are subscribers dropping off?Copy
24Compare the open rate and click rate of every automation I have running. Which one is the strongest and which is dragging?Copy
25Pull the full configuration of my welcome automation and tell me where I'm leaving conversion on the table.Copy
26How many subscribers are currently in progress in each automation, and how long have they been there?Copy
ESubject lines and hooks
27Analyze the subject lines of my 20 best-opened posts. Build me a subject line guide with the patterns, structures, and word choices that worked.Copy
28Find the worst-performing subject lines in my last 6 months and tell me why they likely underperformed.Copy
29Compare subject lines that use questions vs. statements vs. numbers. Which format wins for my audience?Copy
30Score my last 25 subject lines against the CREAM framework (Cultural reference, Real place, Events as access, Abstract nouns, Mystery). Which CREAM elements correlate with my highest opens?Copy
FMonetization
31Show me my product sales by product over the last 90 days. Which is selling, which is sleeping, and which has the best conversion rate from email click to purchase?Copy
32Which posts have driven the most paid product purchases? Pull the post content and tell me what made the CTA work.Copy
33What's my revenue per subscriber and revenue per send? Track it monthly for the last 6 months.Copy
34Suggest 5 sponsor categories matched to my top-performing topics and the audience patterns in my subscriber base.Copy
GSegment building (write access)
35Build a dynamic segment called "Engaged Last 30 Days" of active subscribers who opened at least 3 of my last 10 sends. Show me the segment count after creating it.Copy
36Create a dynamic segment of free subscribers who've opened 5+ emails in the last 30 days but haven't upgraded. Name it "High Intent Free."Copy
37Create a dynamic segment of subscribers who signed up in the last 60 days but haven't opened any email yet. Name it "Cold New Subs."Copy
38Build a static segment of every subscriber who was active during the week I launched my last big campaign so I can track their retention separately.Copy
39Create dynamic segments for each of my top 5 acquisition sources so I can compare engagement and revenue per source going forward.Copy
40Build a segment of subscribers who clicked any link in my last 3 product-related posts but haven't purchased. Name it "Warm Buyers."Copy
06 / Workflows that compound

Six prompts you'll run on repeat.

These are multi-step asks. Save them. Run them on a cadence. They're where the MCP stops being a novelty and starts being a tool.

01. Friday ReviewWeekly

Read Run every Friday morning. Replaces the dashboard scroll.

Pull a Friday review for [publication name]. New subscribers this week vs. last week. Open and click rate this week vs. trailing 4-week average. Top and worst performing post by open rate. Top acquisition source vs. last week. Any active automation that dropped in performance. Three observations about what changed.Copy
02. Content Post-MortemAfter every send

Read Closes the feedback loop while the data is still fresh.

Pull stats on my most recent post. Then pull the full content. Compare it to my top 3 posts of the last 90 days by open rate and click rate. Tell me what worked, what didn't, one subject line lesson, one hook lesson, one CTA lesson, and what to test in the next send.Copy
03. Subject Line LibraryQuarterly

Read Run quarterly. Pin to a doc. Pull from before every send.

Pull every post I've sent in the last 12 months. Rank by unique opens. Group the top 25% by subject line pattern (question, number, curiosity gap, contrarian, direct benefit, name drop). Show me example subject lines from each category with their open rates. Build me a swipe file I can reuse.Copy
04. Acquisition AuditMonthly

Read Monthly. Surfaces channels that are growing, dying, or hidden.

Pull my acquisition sources for the last 30 days, the previous 30 days, and the same 30 days a year ago. Show percentage share for each in each window. Tell me which is growing fastest, which is dying, which converts best to paid, and where I'm under-leveraged.Copy
05. Read, Decide, SegmentAs needed

ReadWrite The first loop that combines insight with the new write capability.

Pull my acquisition sources for the last 90 days. Find the source with the highest engagement rate but the smallest subscriber count. That's an underleveraged channel. Then build a dynamic segment of subscribers from that source so I can target them with a tailored send next week.Copy
06. Engagement TriageBi-weekly

ReadWrite Bi-weekly. Catches churn before the unsubscribe.

Identify subscribers who opened at least 3 of my sends in the 90 days before that, but have opened nothing in the last 30 days. Build a dynamic segment called "Slipping Engaged" so I can target them with a re-engagement send. Then summarize what content they previously engaged with most.Copy

Get the Marketing AI Starter Pack, free.

Marketing AI Playbook is the operator's library for the AI era of marketing. Real prompts, real workflows, no fluff. Grab the Starter Pack and the next operator's guide will land in your inbox the moment it ships.

07 / Stack combinations

The Beehiiv MCP gets stronger when you stack it.

Beehiiv on its own is useful. Beehiiv stacked with your other tools is where solo operators get unfair leverage. Claude can run multiple MCPs in a single conversation. Here are the pairings worth setting up.

Beehiiv + Google Drive

Pull a post from Beehiiv, summarize for a stakeholder doc, save to Drive. Or the reverse: read your editorial calendar in Drive, then audit which planned topics actually shipped.

Pull the full content of my top performing post in the last 90 days. Summarize the strategic insight in 200 words. Save it to my Drive folder titled "Newsletter Wins."Copy

Beehiiv + Notion

If your content calendar lives in Notion, cross-reference planned vs. actual performance.

Pull my last 10 published posts from Beehiiv and match them to entries in my Notion content calendar. Flag posts I shipped that weren't in the calendar, and entries in the calendar that never shipped.Copy

Beehiiv + Web Search

Find what's trending in your niche, then check your coverage gap.

Search the web for the top 5 trending topics in [my niche] over the last 30 days. Compare to my own post topics from the same period. Tell me which trending topics I haven't covered and would naturally fit my voice.Copy

Beehiiv + Typefully

Turn winners into more winners. Take a top-performing newsletter and repurpose it for distribution.

Pull my best-opened post from the last 30 days. Extract the core insight. Draft 3 thread variants for X/Threads in my voice and save them as drafts in Typefully.Copy
CMO Take

The single MCP gives you analysis. The combined MCP stack gives you a distribution flywheel. The newsletter that took 90 minutes to write becomes 6 thread drafts, a Drive summary, and a Notion update without leaving the chat.

08 / Before and after

The same job. A fraction of the time.

Three workflows that used to eat half a day. Same outcome, before and after MCP.

Subject line analysis

Before, ~2 hours

Open Beehiiv. Filter posts by date. Export to CSV. Open the spreadsheet. Sort by open rate. Manually scan the top 10 subject lines for patterns. Try to articulate what the pattern even is.

After, ~3 minutes

"Pull subject lines from my top 25% of posts in the last 6 months by open rate. Group them by structural pattern and tell me which pattern wins for my audience." 40x faster.

Re-engagement campaign

Before, an afternoon

Build a segment manually in Beehiiv. Export it. Cross-reference open behavior. Build a follow-up segment. Verify counts. Hand off to the email tool.

After, one chat

"Build a dynamic segment of subscribers who opened at least one of my last 3 sends but haven't opened anything in the last 30 days. Name it Slipping Engaged." Hours saved.

Friday review

Before, ~90 min, skipped most weeks

Bounce between Beehiiv tabs. Take notes in a doc. Compare to last week. Try to remember what you were tracking. Give up. Hope you'll catch up next week.

After, ~6 minutes

One workflow prompt. Full picture. Mobile-friendly. Done before your second coffee. 15x faster.

09 / Things to know

The operational fine print you'll actually need.

10 / Common mistakes

The traps. Avoid them.

11 / What's next

The MCP keeps opening up. Build on it.

v1 launched read-only. v2 added segment writes. The pattern suggests Beehiiv is opening the surface area incrementally rather than shipping a giant write-everything release. That's the smart way to do it.

What's clear: the Beehiiv MCP is becoming a real operator's interface. You'll still open Beehiiv to design, configure, and ship. You'll increasingly use Claude to ask the questions, run the analysis, build the segments, and surface the patterns. Two surfaces, working together.

CMO Take

The MCP doesn't make you smarter. It makes the data fast enough that you can stop guessing, and now, fast enough to act on what you find without leaving the conversation. That's the whole game.

This is a snapshot of what's possible right now. The MCP keeps evolving. Bookmark the page and check back. I keep it updated as the surface area grows.

Try beehiiv →

This guide is part of Marketing AI Playbook, an operator's library of MCP and AI tool guides for solo marketers and small teams. Built and maintained by Tuck Ross, former Fortune 500 marketing executive.

The Marketing AI Starter Pack is on us.

If you made it this far, you're the kind of operator Marketing AI Playbook is built for. Grab the Starter Pack and the next operator's guide ships to your inbox the moment it's live. Real prompts, real workflows, no fluff.