The Operator's Guide

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

Most creators are using AI to write emails. Operators use AI to run the system. Kit just shipped the bridge.

50 Prompts 10 Workflows 65 Tools Mapped
01 / Why this matters

Email was always the highest-leverage channel. Now it's programmable.

Until last week, AI lived next to your email tool. You drafted in Claude. You copy-pasted into Kit. Copy-paste was the bottleneck.

MCP collapses that. Claude doesn't draft an email for you to paste into Kit. Claude opens Kit, reads your last 12 broadcasts, identifies the three subject lines that beat your average, drafts the next one in that pattern, and creates the draft for you to review. One conversation. No tab-switching.

This is a different relationship with your tools. Less clicking. More thinking. The creators who treat their email system as a programmable surface, not a clickable dashboard, are going to run quietly past the ones still copy-pasting subject lines from a Google Doc.

The Real Shift

Most "AI for email" coverage focuses on copy generation. That's the small win. The big win is operations. Audits, segmentation, list health, re-engagement, sequence editing. The work nobody wants to do that quietly determines whether your business compounds.

This guide is the operator's playbook for that work. 50 prompts. 10 workflows. Setup takes 4 minutes. Then we'll walk through what you can actually do.

02 / Setup

4 minutes. No code.

Step 1. You need a Kit account on Creator or Pro

The MCP is paid-plan-only. The free Newsletter plan does not include MCP access. Creator runs $33 per month at 1,000 subscribers (or $390 per year, saving $78). Pro runs $66 per month at the same level (or $790 per year, saving $158). 14-day free trial, no credit card required.

I use Kit Pro for Marketing AI Playbook. Links in this guide are affiliate links. Same Kit, same price, no extra cost to you.

Start here. Get your Kit account set up before you do anything else. The MCP only works once you're on Creator or above.

Start your Kit account →

Step 2. Connect the MCP in your AI client

The Kit MCP URL is https://app.kit.com/kit-mcp

Compatible clients: Claude.ai, Claude Desktop, ChatGPT, Cursor, Windsurf, Microsoft Copilot, Claude Code.

If you're on Claude.ai (browser): Go to claude.ai/settings/connectors, add a custom connector, paste the MCP URL, and authorize through Kit.

If you're on Claude Desktop: Open Settings, find the Connectors section, paste the MCP URL, and authenticate. A browser tab opens. Select the Kit account, approve access. Tab closes. You're connected. Fully quit and reopen the app once.

Step 3. Approve the first tool call

Kit's MCP defaults to per-call approval. The first time Claude runs a Kit tool, you'll see an approval dialog. This is a feature, not a bug. Three rules for how to use it:

Step 4. Verify with one read

Type this into Claude:

Show me my Kit account growth stats for the last 30 days. Copy

You'll see the approval dialog. Approve it. Claude returns new subscribers, cancellations, and net growth from your live account. The MCP is working.

03 / Capability map

65 tools. 3 risk tiers.

Kit's docs say "50+." The actual count is 65, across 17 categories. Here's the operator's view: what each category lets you do, and which risk tier the tools sit in.

7 tools / Read + Write

Account

Pull email stats, growth stats, identity, brand colors, creator profile. Update brand colors.

10 tools / All tiers

Subscribers

List, get, create, update single or bulk. Filter by engagement and sign-up date. Pull per-subscriber engagement stats. Unsubscribe.

8 tools / Read + Write

Tags

List, create, rename. Tag and untag single or bulk (up to 100 sync, larger batches async).

4 tools / All tiers

Custom Fields

List, create, rename, delete (destructive). Bulk update values across many subscribers.

3 tools / Read

Segments

List segments, get details, get the segment DSL schema for advanced filtering.

3 tools / Read + Write

Forms

List forms and landing pages, list subscribers per form, add subscriber to a form.

7 tools / All tiers

Sequences

List, get, create, update, delete (destructive). Add subscribers to sequences.

5 tools / All tiers

Sequence Emails

List, get, create, update, delete individual emails within a sequence. The killer differentiator.

8 tools / All tiers

Broadcasts

List, get, create draft, update, delete. Per-broadcast stats, account-wide stats, per-link clicks. The MCP never sends. You approve from Kit's UI.

2 tools / Read

Posts

List published posts, get a specific post with full HTML.

5 tools / Read + Write

Snippets, Templates

List email templates. List, get, create, update reusable content blocks.

3 tools / All tiers

Webhooks

List, create, delete webhooks for real-time event delivery to your tools.

5 tools / Read

Authors, Conditions, Content Tags, Meta

List authors, condition sets, content tags. Plus the meta-tool: list_prompt_suggestions.

The three tiers, plainly

Read Safe. Pulls data. Never changes account state. Around 38 of the 65 tools sit here. "Always allow" these and stop worrying.

Write Reversible. Tags, drafts, updates. Around 22 tools. Approve case-by-case until you trust the pattern, then "always allow" the ones you use weekly.

Destructive Irreversible. Around 5 tools: delete broadcast, delete sequence, delete custom field, delete webhook, unsubscribe. Keep manual approval on these forever.

04 / Mental model

Claude is your CMO assistant, not your typist.

Most people approach AI tools like a vending machine. Insert prompt, receive output. The operators who get real value treat it like a junior CMO who happens to have read every marketing book ever written and can pull live data from your tools.

Three principles for getting good answers

1. Be the editor, not the typist.

Ask Claude to pull data and propose options. You decide. "Find my top 5 subject lines and propose 3 patterns I could replicate" beats "Write me a subject line."

2. Chain, don't dump.

Big prompts that try to do five things at once underperform. Walk Claude through the work: pull this, analyze that, draft based on the analysis. The chain becomes the workflow. The workflow becomes the operating system.

3. Stay close to the data.

Ask Claude to cite specific broadcast IDs, subscriber counts, click-throughs. Numbers ground the work and let you verify. "Show me my last 5 broadcasts ranked by open rate, with subject lines and exact open percentages" beats "Tell me which subjects worked."

05 / The 50 prompts

50 prompts organized by what you're actually trying to do.

Most prompt libraries organize by tool. That's useful for engineers. Operators don't think in tools. They think in jobs to be done. Tap any prompt to copy.

A note on data: These prompts work on day 1 or year 3. Claude will tell you when the data is thin. Cross-tool prompts assume you have the relevant MCP connected.

APerformance and analytics
01Show me my last 30 days of growth: subscribers added, cancellations, net change, and sources.Copy
02Which 5 broadcasts in the last 90 days had the highest open rate? Show subject lines and exact percentages.Copy
03Compare my Tuesday, Thursday, and Sunday send performance over the last 12 sends. Open rate, click rate, unsubscribe rate.Copy
04What's my average open rate across the last 30 days, and which broadcasts beat it by 10 percent or more?Copy
05Find the 3 broadcasts with the highest click rate in the last 60 days. What were the top clicked URLs in each?Copy
06Audit my email stats overall: total sent, open rate, click rate, unsubscribe rate, bounce rate. Flag anything outside healthy ranges.Copy
BSubscriber intelligence
07Find my top 50 most engaged subscribers based on opens and clicks in the last 60 days.Copy
08Show me subscribers who clicked any link in the last 30 days but haven't opened anything in the last 7. Lapsing high-intent group.Copy
09List subscribers tagged "VIP" who haven't engaged in 60 days. These are re-engagement candidates.Copy
10Pull subscribers who signed up via [form name] in the last 14 days. Show their state and any custom fields.Copy
11Show me which custom fields are most populated across active subscribers. Identify the data hygiene gaps.Copy
12Find subscribers who clicked [specific URL] in the last 90 days. Show how many times each.Copy
CList health and cleanup
13Identify subscribers who haven't opened any email in the last 90 days. Count them. Show the oldest 20.Copy
14List bounced and complained subscribers from the last 30 days. These need cleanup.Copy
15Show me my list growth rate vs cancellation rate over the last 6 months. Is the trend healthy?Copy
16Which forms have the highest sign-up rate and which are underperforming? Show subscribers per form sorted by volume.Copy
17Audit my tag list. Show tags with under 10 subscribers, and flag potential duplicates by name similarity.Copy
18Show me subscribers without first names. Data quality cleanup candidates.Copy
DContent and broadcast drafting
19Read my last 5 broadcasts and identify the patterns in my best-performing subject lines. What's the framework?Copy
20Draft a broadcast in my voice on [topic] for [audience tag], using my last 3 broadcasts as voice reference. Create the draft.Copy
21Suggest 10 subject line variants for this draft, ranked by which one I'd most likely use based on my history.Copy
22Draft a re-engagement broadcast for subscribers tagged "inactive 90+." Tone: warm, not desperate. Create the draft.Copy
23Read my last 3 newsletters and find a thematic thread I can pull on for the next issue.Copy
24Write 4 preview text variants for this broadcast: punchy, curiosity, value, contrarian. Rank them.Copy
ESegmentation and targeting
25Build a target list of subscribers who opened the last 5 broadcasts AND clicked a link in the last 30 days. Show the count.Copy
26Find subscribers tagged "course-customer" who haven't received the [sequence name] sequence yet.Copy
27Identify subscribers in 3 or more tags (deeply engaged) vs subscribers in only 1 tag (lightly engaged). Show the split.Copy
28Pull subscribers in segment "[name]" who joined in the last 30 days. These are the freshest deep-engaged group.Copy
29Build a target list: signed up via [form] AND clicked [URL] AND tagged [tag]. Show me the count and a sample.Copy
30Show me untagged subscribers from the last 30 days that need categorization. These are the cleanup queue.Copy
FSequences and automations
31Show me every sequence in my account with subscriber count and last edited date. Which ones are stale?Copy
32Audit my [sequence name] sequence: how many emails, what's the cadence, current subscriber count, and what's the drop-off pattern?Copy
33Find sequences with under 10 active subscribers. These are candidates for deletion or revival.Copy
34Read all emails in my [sequence name] sequence and identify any that contradict each other or repeat the same idea.Copy
35Draft a new sequence email for position [X] in [sequence name], matching the voice and pacing of the prior emails.Copy
36Show me the subscribers currently in the [sequence] sequence and where they are in the flow. Anyone stuck?Copy
GTagging and lifecycle
37Tag every subscriber who clicked [URL] in the last 30 days with [new tag]. Use bulk tagging.Copy
38Apply [tag] to all subscribers who signed up via [form] in the last 7 days. Use bulk tagging.Copy
39Build a "Welcome Series Complete" tag. Tag subscribers who've been on the list 30 or more days. Use bulk tagging.Copy
40Remove [old tag] from all subscribers and apply [new tag] in its place. Clean migration.Copy
41Tag subscribers who opened 5 or more broadcasts in the last 30 days as "Engaged - High."Copy
42Find tags with duplicate intent (e.g. "course" and "courses") and propose a clean merge plan.Copy
HMonetization and cross-tool

These assume you have the relevant MCP connected. Stripe and Meta have public MCPs. ThriveCart-style commerce MCPs are coming.

43Pull my Stripe revenue YTD via the Stripe MCP, then tag every paying customer in Kit with "Paying Customer."Copy
44Identify subscribers who clicked the [product URL] in the last 90 days but haven't purchased. These are warm leads.Copy
45Cross-reference my Kit "paying customer" tag with my checkout platform's customer list. Show drift and gaps.Copy
46Find subscribers in the [free product] sequence who haven't opened in 14 days. Draft a re-engagement nudge.Copy
47Tag every subscriber who clicked an affiliate link in my last broadcast with "Affiliate Clicker - [date]."Copy
48Build a segment of high-LTV indicators: VIP tag + 60-day engagement + paying customer tag. Show the count.Copy
49Pull last month's broadcast click data and identify my top 5 revenue-driving subject lines (by click-to-product-page rate).Copy
50Audit my newsletter sponsor click-through rates over the last 6 broadcasts. Which sponsors performed best and which underperformed?Copy
06 / Workflows that compound

10 workflows. Each one runs in under an hour.

Single prompts are nice. Workflows are where the leverage lives. Each of these is a chain of prompts that produces a real operating outcome.

01. Friday Performance Review15 to 25 min / Weekly

Read Pull the week's broadcast stats, identify winners and losers, capture lessons for next week.

  1. Pull broadcast stats for sends in the last 7 days, ranked by open rate.
  2. Compare each broadcast's open and click rates to your trailing 30-day average.
  3. Identify the top performer and bottom performer. Ask Claude to summarize the pattern.
  4. Capture three sentences in a running performance log. Use a Drive or Notion doc.
  5. Note one thing to test next week.
02. Weekly Newsletter Drafting30 to 45 min / Weekly

ReadWrite The gateway use case. Draft this week's newsletter with your voice and your data.

  1. Pull your last 3 newsletters with full content. Ask Claude to identify your voice signature.
  2. Pull your top 5 broadcasts by engagement in the last 60 days. Identify a thematic thread.
  3. Draft this week's newsletter in your voice, riffing on the thread.
  4. Generate 5 subject line variants and 4 preview text variants. Pick the best of each.
  5. Create the draft via create_broadcast. Claude returns a confirm_url. Open it, review in Kit, schedule from there.
03. Subject Line Pattern Mining20 to 30 min / Weekly

Read Find what's actually working in your subject lines so you stop guessing.

  1. Pull your last 30 broadcasts with subject line and open rate.
  2. Identify the top decile by open rate. Get exact percentages.
  3. Ask Claude to extract the pattern: word count, structure, hook type, punctuation, length.
  4. Have Claude propose a 5-subject-line framework for next week based on the pattern.
  5. Save the framework. Update monthly.
04. Monthly List Health Audit30 to 45 min / Monthly

ReadWrite The maintenance pass that keeps deliverability healthy.

  1. Pull bounced and complained subscribers from the last 30 days. Note the count.
  2. Pull subscribers with no opens in the last 90 days. Note the count.
  3. Identify candidates for a sunset sequence. Apply a "Sunset Candidate" tag in bulk.
  4. Draft a final re-engagement broadcast targeted at the sunset candidates. Tone: warm, last chance, opt-out friendly.
  5. Create the draft. Review in Kit. Schedule.
05. Re-engagement Campaign Build45 to 60 min / Quarterly

ReadWrite Build a 3-email re-engagement sequence from inactive subscriber data.

  1. Find subscribers inactive for 90+ days. Segment by their past engagement signal (heavy past clickers vs casual openers).
  2. Draft 3 re-engagement emails. Email 1: warm hello and acknowledgment. Email 2: best work reminder. Email 3: opt-in to stay.
  3. Create each as a sequence email via create_sequence_email.
  4. Add the segment to the new sequence.
  5. Review the full sequence in Kit. Activate from there.
06. Tag Hygiene Sweep45 to 60 min / Quarterly

ReadWriteDestructive Audit every tag, kill duplicates, fix orphans. Approve destructive actions manually.

  1. List every tag with subscriber count. Sort low to high.
  2. Flag tags with under 10 subscribers as cleanup candidates.
  3. Identify tags with duplicate intent (course / courses, vip / VIP / vips).
  4. For each duplicate cluster, propose a merge plan: which tag wins, which gets renamed or deleted.
  5. Approve each delete manually. Untag duplicates in bulk. Apply the canonical tag in bulk.
07. Cross-MCP Customer Sync30 to 45 min / Monthly

ReadWrite Sync your paying customers across Kit and your commerce stack so segmentation stays clean.

  1. Pull your customer list from your commerce MCP (Stripe, ThriveCart when it ships, or other).
  2. Pull subscribers tagged "Paying Customer" in Kit.
  3. Identify the drift: customers not tagged in Kit, and Kit tags that don't match a customer record.
  4. Apply "Paying Customer" tag to missing entries in bulk.
  5. Flag mismatches for manual review.
08. Quarterly Audience Architecture Review60 to 90 min / Quarterly

Read The strategic step-back. Generate a one-page CMO-style report for your own business.

  1. Pull growth stats for the quarter: net new subs, cancellations, growth rate.
  2. Pull source attribution: which forms drove the most volume, which drove the highest engagement.
  3. Pull engagement cohorts: deeply engaged, lightly engaged, lapsed.
  4. Pull segment performance: which audiences open and click vs which are dormant.
  5. Ask Claude to assemble a one-page narrative. Read it like you'd read a board update for your own company.
09. Voice Memo to Broadcast10 to 15 min / As needed

ReadWrite Capture an idea the moment you have it. Turn a 3-minute voice memo into a drafted broadcast before the thought fades.

  1. Record a voice memo describing the newsletter you want to send. Topic, main point, any specific details. 2 to 4 minutes is enough.
  2. Attach the memo to a Claude conversation. Prompt: "Transcribe this, then draft a broadcast email in my voice based on my last 10 broadcasts. Push it to Kit as a draft for me to review."
  3. Claude pulls your recent broadcasts for voice reference, writes the email, and creates the draft via create_broadcast.
  4. Open Kit. Review the draft. Edit as needed. Schedule.

Removes the "I'll write it later" barrier. The moment the idea shows up is when it's sharpest.

10. Email Archive to Content Library90 min setup / Self-updating weekly

Read Every creator with a long sending history is sitting on a content library they've never had time to organize. This workflow builds it once and keeps it current.

  1. Pull every broadcast since your account start date. Include subject lines, body copy, open rates, and click rates.
  2. Ask Claude to categorize them by topic, tag which products each one was promoting, and flag evergreen emails worth reusing in funnels.
  3. Save the organized database to a Notion or Drive doc. Label tabs by category.
  4. Set a recurring prompt for Monday mornings: "Add last week's new broadcast to the right category in my email archive."
  5. Review the evergreen flagged list quarterly. Repurpose the best into welcome sequences and evergreen funnels.

Two to four years of broadcasts you've forgotten about is a content goldmine. This workflow unlocks it.

Run these every quarter and the system runs without you. Workflows are the part most creators skip. They're also the part that compounds.

Try Kit and run them yourself →

Bonus workflow: Newsletter Sponsor Reporting. If you run sponsored sends, build a recurring workflow to pull broadcast stats and sponsor-specific click data, then draft a sponsor report email. Same shape as the others. Different audience.

From Kit's team: Kit published their own day-one workflow breakdown covering 10 workflows from beta creators, including real use cases from newsletter writers, coaches, and course creators. Worth reading alongside this guide. Read Kit's official guide →

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

Kit MCP gets more powerful when it's not alone.

An MCP on its own is useful. Multiple MCPs in the same conversation is where the leverage compounds. Here are the combinations worth thinking about.

Kit + Stripe MCP

Pull revenue data. Identify paying customers. Tag them in Kit. Build a "high-LTV" segment that crosses purchase value, engagement, and tenure. Run monthly to keep the segment fresh.

Kit + Meta MCP

Sync Custom Audiences from Kit segments to Meta. Build lookalike audiences from your most engaged subscribers. Run a Meta campaign targeting an audience that mirrors your top decile. Pull the campaign results back into Claude to assess.

Kit + Google Drive / Docs MCP

Pull research from a Google Doc and drop it into a broadcast draft. Save broadcast reports to a Drive folder. Read meeting notes and draft a relevant newsletter. The unsexy combo that saves hours weekly.

Kit + CRM MCP

For B2B operators, bidirectional sync of subscriber-as-lead. Find Kit subscribers who match your CRM's ICP criteria. Tag them for VIP nurture. Pull CRM stage data back to Kit for segmentation.

Kit + commerce MCP (coming)

When ThriveCart, Lemon Squeezy, or other commerce platforms ship MCPs, the customer sync workflow gets much cleaner. For now, do it manually monthly with the data you can pull. The pattern is the same.

08 / Kit MCP vs Beehiiv MCP

The honest comparison most creators won't write.

Both Kit and Beehiiv shipped MCPs. They're not the same. Here's the head-to-head from someone who built operator's guides for both.

DimensionKit MCPBeehiiv MCPEdge
Total tools6556Kit
Approval modelPer-call by defaultPer-sessionKit (safer), Beehiiv (faster)
Send and schedule via AINo, returns confirm_urlYes, full schedulingBeehiiv for speed, Kit for safety
Engagement filteringAtomic, AND-able, scoped to broadcasts and URLsSegment DSL (SQL-like)Kit for AI-driven assembly, Beehiiv for power users
Sequence email editingFull read and writeRead onlyKit
Built-in prompt catalogYes (list_prompt_suggestions)NoKit
Bulk operationsFirst-class, async over 100YesTie
Cross-tool compositionStrong via standard MCP patternsStrong via standard MCP patternsTie
DocumentationNotion hub plus help docsDeveloper portal plus help docsTie
PricingCreator plan and above ($33/mo)Most paid plansTie
My read after building guides for both

Beehiiv's MCP is faster to ship a broadcast end-to-end. Kit's is more architecturally cautious and more powerful for ongoing list operations. If your business is built on automated sequences, Kit's deeper sequence-email write access matters. If your business is broadcast-heavy and you trust AI to send, Beehiiv's send-tools save real time. Both are good. They're optimizing for different operators.

For most solo marketers and small teams, the deciding factor isn't the MCP. It's the underlying platform: deliverability, automation depth, monetization features, community. The MCP is the multiplier. Pick the platform that fits your business, then use the MCP to run it.

If you're choosing between them or migrating, this is the link.

Start with Kit →
09 / Before and after

The same job. 10x less friction.

Three operational tasks every Kit user runs. Same job, before and after MCP.

Finding your most engaged subscribers

Before

Open Kit. Click Subscribers. Filter by tag. Adjust date range. Export to CSV. Open in Sheets. Sort by activity. Look for patterns. Switch back to Kit. Apply tags manually.

After

"Find subscribers tagged X who clicked URL Y in the last 30 days, and tag them Z." Done in 20 seconds.

Identifying your top-performing broadcasts

Before

Click through 20 broadcasts manually. Note the open rate for each in a spreadsheet. Sort. Try to remember which subject lines worked. Lose track. Start over.

After

"Rank my last 90 days of broadcasts by open rate. Show me subject lines and exact percentages." 15 seconds.

Auditing a sequence for weak spots

Before

Open the sequence. Click each email. Read it. Try to remember what the previous one said. Wonder which one has the lowest open rate. Click into stats. Repeat.

After

"Audit my onboarding sequence. Identify the email with the lowest open rate. Propose three rewrites in my voice." 90 seconds.

10 / Real operator. Real results.

What a power user found in a single day.

Dan Cumberland runs a 12,000-subscriber list and had built his own Python analytics scripts and browser automation just to get data Kit's UI couldn't surface. Then he spent one day with the Kit MCP. What he found is worth reading before you run your first workflow.

Dan's story was documented by Cait Miller on the Kit blog. The full case study is here. What follows is the operator's summary.

Five questions he'd never been able to answer before

Dan didn't come in looking to replace what he already had. He came in to find what was previously unaskable. He found five things.

1. Who used to love my emails and then disappeared?

Kit's segment builder can't combine "opened 30+ times historically" with "zero opens since March." The MCP can. Dan ran three cohorts with tightening thresholds and landed on 815 subscribers who had been deeply engaged and then went completely dark. That's a re-engagement sequence with a warm lead pool that didn't exist before he asked the question.

Look at my Kit account. Find subscribers who opened 30+ broadcasts before [date] but have zero opens since. Rank them by how engaged they used to be, and tag the top 100 as 'loyal-then-gone' for a re-engagement sequence. Copy

2. What percentage of my list actually matches my ideal customer?

Dan sells consulting to architecture, engineering, and construction firms. He'd wanted a hard ICP penetration number for years. The answer had always required a CSV export and three to four hours of manual classification. With the MCP, he sampled 600 subscribers across six paginated calls, cross-referenced industry field, title keywords, and company name — and had his number in 10 minutes. About 4.5% of his list matched his ICP. That's roughly 570 people, not 12,000. That one number changed how he thinks about list-building.

Sample 600 active subscribers from my Kit list. For each one, check the industry custom field, the job-title keyword, and the company-name keyword against my ICP profile. Tell me what percentage of my list matches, broken out by decision-maker, manager, and IC. Copy

3. Which lead magnets actually produce paying customers?

Dan pulled his full purchases list, sampled high-value buyers, and traced each one back to their original opt-in form using Kit's kit_first_form custom field. One $2,000 cohort buyer traced back to a specific lead magnet he might have otherwise deprioritized. Before the MCP, that attribution pass took roughly 10 minutes per buyer through the Kit UI. Across a quarterly review, that's an eight-hour project nobody runs. With the MCP, it's 30 minutes.

Pull my last 90 days of purchases. For each buyer, look up their kit_first_form custom field to trace which lead magnet they originally opted in through. Rank my lead magnets by total revenue and average buyer LTV. Tell me which one is producing the most paying customers. Copy

4. What does my entire automation architecture actually look like?

Three parallel MCP calls — sequences, forms, tags — plus a walk of the exclusion rules on each sequence, rendered as a Mermaid flowchart. Fifteen minutes. Dan's diagram revealed a four-way role-routing split he'd built over time but had never seen mapped end-to-end. It also surfaced roughly 25 retired sequences from a previous brand era still marked active in Kit. An automation graveyard, invisible until someone went looking.

Pull my full list of sequences, forms, and tags from Kit. For each sequence, walk the exclude_subscriber_sources field to determine the role-routing logic. Render the full nurture architecture as a Mermaid flowchart, showing how subscribers move through the system from form opt-in to closer sequence. Copy

5. Which subject lines actually work for my audience, and why?

Dan pulled his 30 most recent broadcasts with open rates, hand-derived a scoring rubric from his top performers, and generated new subject line variants scored against that rubric. The top scorer was "I stopped selling AI tools to engineering firms" — matching the first-person confession pattern his list historically responds to. What had been 20 to 30 minutes of inconclusive brainstorming per send is now a three-minute exercise, trained on his actual data, not generic best practices.

Pull my 30 most recent broadcasts with their subject lines and open rates. Identify the patterns in my top 10 performers. Build a scoring rubric. Then take this draft subject line [paste yours] and generate 5 variants that match my historical patterns. Score each variant against the rubric and tell me which to send. Copy
What this actually means

Dan had built Python scripts and browser automation just to ask better questions about his own list. The MCP didn't replace his rigor. It made his questions answerable without the scaffolding. If a power user found eight things he hadn't known about a list he'd managed for years, the question isn't whether your list has similar gaps. It's which ones you'll find first.

11 / Things to know

The operational fine print you'll actually need.

12 / Common mistakes

The traps. Avoid them.

13 / What's next

This is the operator-friendly era of email. Build for it.

Kit shipped 65 tools on day one. They've signaled more are coming. The MCP isn't the destination. It's the new starting line.

Three things to expect over the next 12 months:

1. More MCP tools.

Kit will keep expanding the surface area. Watch for tools that close the remaining gaps: automation creation, sequence email deletion, deeper template control.

2. More MCPs to combine with.

Every major SaaS is shipping or considering an MCP. The operators who plan for cross-MCP composition will run circles around the ones still working tool-by-tool.

3. A new operator class.

The creators who treat email as a programmable surface, not a clickable dashboard, will compound faster than the ones still copy-pasting subject lines. Not because they're working harder. Because the system is doing the work.

This is where it starts. Kit Creator or above. Connect the MCP. Run a few workflows. Watch what changes.

Build it on Kit →

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.