4 ways to connect Mailchimp to Claude in 2026 (the easy way)

Prerequisites

• A Porter Metrics account with your Mailchimp account connected (free tier is enough to try it end-to-end)
• A Claude account — the free plan works for Claude Web; a Pro subscription is needed for Claude Code and Desktop MCP features
• Admin or standard access to the Mailchimp audiences you want to connect

Connect Mailchimp to Claude with MCP

For this tutorial we’re going with the MCP method. Here’s a quick explainer of what MCP is and why it’s the best path for Mailchimp.

MCP (Model Context Protocol) is the open standard that lets AI tools like Claude, ChatGPT, Claude Code and others access and use external APIs — the things that make tools like Mailchimp work under the hood. Instead of building a custom integration for every AI tool you use, you install one MCP and every compatible AI gets access to the same data.

Four reasons MCP wins for Mailchimp:

The full setup takes under 5 minutes and breaks into three moves: connect Mailchimp to Porter, point Claude at the Porter MCP, and ask your first question.

1. Connect your Mailchimp data to Porter

Porter sits between Mailchimp’s Marketing API and Claude. It handles OAuth, rate limiting, pagination and all the plumbing so Claude only ever sees clean, structured data.

Sign up for Porter. Create a free account at portermetrics.com. The free tier is enough to run this full workflow end-to-end.

Connect your Mailchimp account. In Porter, click Create → pick Claude as the destination → select Mailchimp as the source → sign in with Mailchimp to grant access to your audiences.

Select your audiences. Choose the Mailchimp audiences you want Claude to query. When you select multiple audiences under a single connection, Porter automatically blends their data together so you can query them as one.

Optional: enable automatic BigQuery storage if you’re connecting multiple audiences with large data volumes. This keeps Claude’s responses fast even at scale.

2. Connect the MCP to Claude

Porter’s MCP URL is what you paste into Claude. Once added, Claude can query Mailchimp data on demand in any conversation.

Go to claude.ai and click the + icon in the chat input to open the tools menu.

In the menu that opens, hover over Connectors and click Manage connectors.

In the Connectors panel, click the + button at the top of the list to start adding a new connector.

Pick Add custom connector from the dropdown that appears.

A dialog opens with the name and URL fields. Type Porter in the first field to name the connector.

In the second field, paste https://mcp.portermetrics.com/mcp. Leave the advanced settings alone.

Click Add at the bottom right of the dialog. Claude opens a sign-in window — use the same Google account linked to your Porter workspace and approve access.

Once the authorization finishes, you’ll see Porter’s read-only tools appear in the connectors panel. You’re ready to start asking questions.

For a fuller walkthrough with screenshots at every step, see the Porter MCP tutorial.

3. Start building questions and dashboards

With Porter connected, open a new Claude chat and ask anything about your Mailchimp in plain English. Claude calls Porter behind the scenes, pulls live data from Mailchimp, and answers with tables, charts, or summaries.

Try one of these to verify the setup is working:

For a full catalogue of copy-paste prompts organized by use case (performance, fatigue, budget, agency, B2B, e-commerce, cross-channel), jump to the prompts section below.

Alternative ways to connect Mailchimp to Claude

MCP is the path we just walked through — and the one we recommend for most marketers. But it’s not the only way to get Mailchimp data in front of Claude. The most common alternatives are Mailchimp’s direct API (or its official MCP if it has one), a live Google Sheets bridge, and BigQuery for scale. Each has its trade-offs — pick the one that fits how your team already works.

• 🔌 Mailchimp’s direct API (or official MCP) — Talk to Mailchimp’s Marketing API yourself, or install Mailchimp’s native MCP if one exists. Maximum control, but you handle auth, rate limits and pagination — and you only get one source.
• 📊 Google Sheets — Live Sheet or one-off CSV upload. Auditable, familiar, faster for big exports — but aggregation happens in the Sheet, not the API.
• 🗄️ Google BigQuery — For large audiences or agencies running multi-audience analysis. BigQuery aggregates; Claude only queries pre-built summaries.

Via Mailchimp’s direct API (or official MCP)

If you’re building a product around Mailchimp — or you’re a developer who’d rather own every layer of the integration — the most direct path is talking to Mailchimp’s Marketing API yourself, or installing the official Mailchimp MCP (if one exists). Mailchimp doesn’t ship an official MCP yet, so this means writing API calls directly in Claude Code or in your own scripts. You’ll need to follow Mailchimp’s rate limits & quotas and request a Developer Token / API access where applicable. Either way, you skip Porter entirely and call Mailchimp from your own code or from Claude Code with raw HTTP requests.

Via Google Sheets (live Sheet or manual CSV)

If your team already lives in Google Sheets — or you want a paper trail before Claude touches anything — feed Mailchimp into a Sheet, then let Claude read the Sheet. You can automate the Mailchimp → Sheets pipeline with Porter so it refreshes daily, or do one-off CSV exports from Mailchimp’s native UI for static analysis.

Read the full Sheets tutorial →

Via Google BigQuery (for scale)

This is the path most people overlook — and it’s the one that saves you when your Mailchimp audience gets serious. A single large subscriber base or an agency managing 10+ audiences will hit API rate limits and latency problems querying Claude directly. Claude will literally tell you it’s taking too long or timing out on big pulls.

BigQuery fixes that. You load Mailchimp data into BigQuery tables on a schedule, then connect BigQuery to Claude — either through a BigQuery MCP or via Claude Code with SQL queries. Instead of asking Claude to pull raw Mailchimp data, you let BigQuery aggregate into small, optimized tables, and Claude only queries the summarized output. Scale problem solved.

Read the full BigQuery tutorial →

Connecting Mailchimp to Claude Code

Most marketers lump Claude and Claude Code together and miss the biggest advantage of the entire MCP ecosystem. They’re not the same tool — and the difference matters enormously once you start working with Mailchimp data seriously.

Claude is a chat interface. You ask a question, Claude pulls live data through the MCP, answers, maybe builds a quick dashboard inside the conversation. Great for one-off analysis. The problem: everything is ephemeral. Want to refresh the dashboard tomorrow? You regenerate it from scratch. Want the same report every Monday? You re-ask the question every Monday.

Claude Code is Claude running inside your computer’s terminal. Because it has access to your filesystem, runtime, and other developer tools, it doesn’t just answer questions — it can build real software. Persistent scripts, scheduled routines, HTML apps, internal dashboards, integrations that run 24/7 without your input. Once it’s connected to Porter’s MCP for Mailchimp, a whole category of work becomes possible.

What Claude Code unlocks that Claude alone cannot

This is where the MCP ecosystem pays off most. Because Claude Code can combine Porter’s MCP with other MCPs — Firecrawl for web scraping, Airtable for structured data, Notion for wikis, Vercel for deployment, Slack and Gmail for delivery — you’re no longer querying data. You’re building tools.

🛠️ Build your own campaign performance dashboard Stack: Porter MCP + Vercel MCP (or Cloudflare Pages, Netlify) Feed Claude Code your Mailchimp targets and goals — open rate goals, list growth targets, bounce rate thresholds — and ask it to generate a custom campaign ROI dashboard for each client. It builds the HTML, pulls live data, deploys to a URL. No Data Studio embed to break when the vendor changes pricing, no template constraints. The dashboard updates automatically because it queries Porter’s MCP on every page load. Best for: agencies that want white-label client dashboards without Looker or Data Studio dependencies.

🔍 Full competitor + performance monitoring Stack: Porter MCP + Firecrawl MCP Combine your own Mailchimp performance from Porter with competitor email campaigns and subject lines from their public archives scraped via Firecrawl. Claude Code stitches both into a weekly competitive intelligence report — your numbers next to their send frequency and engagement tactics, with an LLM summary on top of what changed week over week. Runs on cron, lands in your inbox every Monday morning. Best for: in-house teams that need market context, not just internal numbers.

📚 Internal marketing wiki with live metrics Stack: Porter MCP + Airtable MCP (or Notion MCP) Use Airtable or Notion as the schema, Porter as the data source. Claude Code keeps every page populated with current open rate, click rate, and bounce rate for every audience — no stale screenshots, no copy-paste from Excel. New hires read one wiki entry and have full context on a client’s account. Best for: agencies and ops teams onboarding analysts or rotating account managers frequently.

🔔 24/7 alerts on open rate drops, list growth stalls, and bounce rate spikes Stack: Porter MCP + Slack MCP (or Gmail MCP) A Claude Code routine on cron pulls Mailchimp via Porter, evaluates thresholds — open rate drops below 15%, bounce rate spikes above 5%, list growth stalls for 7 days — and pushes Slack or Gmail alerts the moment something crosses the line. You stop checking dashboards reactively; the dashboard checks itself and tells you when to look. Best for: any team that’s ever discovered a problem 48 hours too late because nobody opened the report.

Bottom line: Claude is for quick questions and ad-hoc dashboards. Claude Code is for building apps, live dashboards, alerts, and actual tools — anything you want to run on its own without re-asking. Same Porter MCP URL works in both, so you don’t pick once and lock in.

Use cases — what you can actually do once Mailchimp is connected to Claude

Getting the connection right is half the battle. The real value shows up in what you do next. Here are the use cases Porter users build around their Mailchimp data — from simple Q&A to full client-facing workflows.

1. Chat and ask questions directly

The simplest use case — and still the one 80% of marketers start with. Open Claude, ask a question, get an answer grounded in live data.

It’s the fastest way to replace a daily Mailchimp reports check-in. But chat is table stakes — the interesting use cases come next.

2. Blend Mailchimp with your revenue data (Shopify, Stripe, HubSpot)

This is where a 360° view gets real. When you connect Mailchimp and your revenue source (Shopify for e-commerce revenue, Stripe for payment data, HubSpot for lead quality), Claude can map email campaigns to actual purchases or closed-won deals — using campaign names, send dates, and member tags — and give you revenue attribution that no platform-side number can.

Claude handles the campaign names, send dates, and member tags mapping and joins. You get a client-ready revenue attribution report that no single platform can generate on its own.

3. Automated alerts and notifications on Slack or Gmail

With Claude Code you can turn Mailchimp monitoring into a routine that runs on its own. Hook Porter’s MCP (for the data) together with a Slack or Gmail MCP (for delivery), then write a Claude Code scheduled task that pulls performance every morning and pings you only when something actually needs attention.

No dashboards, no daily check-ins. The report comes to you — and only when it matters.

4. Client-ready presentations with live data (Gamma, HTML, PDF)

A common agency pain: you send clients a Mailchimp report export, Excel pivot breaks, the client panics. With Claude you can build the presentation itself — as a Gamma deck, a custom HTML page, or a PDF — populated with live numbers each time.

The presentation becomes a delivery artifact you send to the client, not a dashboard that depends on another tool staying up. No broken iframe, no login prompts, just the content.

Mailchimp fields and metrics you can query with Claude

Before you start writing prompts, it helps to know what data is actually available. Porter MCP gives Claude access to 204 Mailchimp fields and metrics across every reporting level, plus breakdowns by campaign, member status, tag, and date. And the same MCP URL also unlocks 25+ other sources — so Claude can blend Mailchimp with Google Ads, GA4, Shopify, HubSpot and more in a single prompt.

Time

DateDay of week (Mon – Sun)WeekMonthQuarterYearMonth and yearQuarter and year

Campaign

Automatic tweetCampaign archive URLCampaign resendableCan be canceledCurrency codeE-mails sentFacebook likesPreview text

List

Address 1Address 2CityCompanyCountryDefault from emailDefault from nameDefault language

List members

E-commerce average orders revenue membersMember average click-through rateMember consents 1:1 messagingMember contact IDMember coordinatesMember countryMember country codeMember currency code

A/B testing

A/B test send dateA/B test sizeA/B test wait timeA/B test winner campaign IDA/B winner criteriaAbuse reports AAbuse reports BBounces A

Campaign details

Campaign creation dateCampaign folder IDCampaign IDCampaign last click dateCampaign last open dateCampaign nameCampaign statusCampaign type

Email content

AuthenticateCampaign hour of the dayContent typeFrom nameReply toSubject lineTo nameUse of auto footer

Bounces

Campaign bounce rateCampaign bouncesCampaign hard bounce rateCampaign hard bouncesCampaign soft bounce rateCampaign soft bouncesCampaign syntax error bounces

Industry benchmarks

Industry abuse rateIndustry bounce rateIndustry click rateIndustry open rateIndustry typeIndustry unopen rateIndustry unsubscribe rate

Automation details

Automation creation dateAutomation IDAutomation nameAutomation start dateAutomation statusAutomation type

Campaign insights

Campaign delivery rateCampaign emails canceledCampaign open rateCampaign opensUnique opens

List all-time totals

List average subscriptions per monthList target growth rateList total campaignsList total contactsList total members

Clicks

Campaign click rateCampaign total clicksCampaign unique clicksCampaign unique subscriber clicks

E-commerce

E-commerce average orders revenue campaignE-commerce total ordersE-commerce total revenue

List insights

List cleaned membersList emails sentList unsubscribed members

Abuse reports

Campaign abuse rateCampaign abuse reports

Campaign forwards

Campaign forward opensCampaign forwards

Automation

Workflow title

For the complete reference, see All Mailchimp fields and metrics.

Prompts you can copy-paste today

1. For agencies

When you need client-ready reports and multi-account campaign summaries.

2. For DTC & e-commerce

When you need revenue attribution and subscriber value analysis.

3. For B2B marketers

When you need list health, lead nurture, and subscriber quality insights.

4. Cross-channel

When you need to blend Mailchimp with Shopify, HubSpot, Google Ads, or other sources.

Limits, safety, and best practices for Mailchimp via Claude

This is the closest thing to a “ban story” for Mailchimp API usage: not an account ban, but a security breach caused by leaked or poorly secured API keys. In 2024, Mailchimp itself was targeted in phishing campaigns that exposed subscriber data from services like Have I Been Pwned (scworld.com, Mailchimp phishing exposes Have I Been Pwned subscribers). For marketers using Claude or MCP integrations, the real cost isn’t a suspended Mailchimp account — it’s exposing your entire audience database because an API key was hardcoded in a prompt, shared in a chat log, or stored without rotation. Unlike Meta Ads, where the fear is “will my ad account get banned?”, the Mailchimp risk is quieter but costlier: a single leaked key can export every email, tag, and segment you’ve ever collected.

Mailchimp’s enforcement is abuse-complaint-driven and quota-based, not tool-based. Mailchimp doesn’t ban accounts because you used Claude or an MCP. It throttles or suspends because of how the API was used: hitting the 10 concurrent connection limit, exceeding 20 message searches per minute, or triggering Omnivore’s abuse-prevention algorithm through high spam complaint rates. Read-only API calls for campaign metrics, audience lists, and engagement data are safe. Write-at-scale (bulk unsubscribes, mass campaign sends via API) or bursty parallel requests are not. The platform’s automated systems reward predictable, low-volume read patterns — exactly what an MCP-powered analysis workflow produces.

What actually goes wrong when scaling Mailchimp via Claude

After reviewing official docs and community threads, two patterns come up again and again.

1. Leaking or misconfiguring API keys. Hardcoding a Mailchimp API key in a Claude prompt, sharing it in a team chat, or storing it in an unencrypted document exposes your entire audience database. In 2024, Mailchimp was the target of multiple phishing and API security incidents that exposed subscriber data at scale (approov.io, How Poor API Security Led to Major Breaches in 2024; scworld.com, Mailchimp phishing exposes Have I Been Pwned subscribers). What to do instead: Use OAuth-based authentication where possible, rotate keys quarterly, and never paste API keys into LLM chat windows. Porter MCP handles key storage server-side — the key never touches your local prompt.

2. Exceeding rate limits with parallel or bursty API calls. The Mailchimp Marketing API enforces a 10 concurrent connection limit (Mailchimp Developer Docs: Fundamentals), and the message search endpoint is capped at 20 searches per minute with a mandatory 60-second retry window after hitting the limit (Mailchimp Release Notes). Running multiple Claude-generated scripts in parallel — or asking Claude to “search all campaigns from the last 2 years” in a single burst — will trigger 429 Too Many Requests errors and temporarily block your access. What to do instead: Batch requests, add intentional delays between calls, and use the async batch endpoint for large data pulls. Porter MCP enforces built-in backoff and per-account batching to stay under these thresholds automatically.

3. Triggering Omnivore abuse prevention through high spam complaint rates. Mailchimp’s Omnivore algorithm monitors abuse complaints (spam reports) per campaign. While this isn’t an API-specific risk, marketers who use API-driven sending without proper list hygiene can hit suspension thresholds. The official policy states that accounts with excessive abuse complaints receive warnings and sending halts (Mailchimp Help: About Abuse Complaints). What to do instead: Never use the API to send to cold or purchased lists. Keep abuse complaint rates below industry standard (under 0.1%). Porter MCP is read-only by default — it does not send campaigns, so this risk is eliminated entirely.

Both behaviors trigger abuse-complaint-driven and quota-based enforcement. If you want to use Claude for Mailchimp safely, stick to read-only analysis via Porter MCP, rotate credentials regularly, and never paste API keys into chat windows.

The 5-rule best-practice protocol

Based on Mailchimp’s documented rate limits, quotas, and policies and the behaviors that have actually caused data exposure or throttling — not guesswork:

• Limit simultaneous API connections to 10. The Mailchimp Marketing API enforces a hard cap of 10 concurrent connections; exceeding this triggers 429 errors (Mailchimp Developer Docs: Fundamentals). If ignored, your analysis scripts will fail mid-run and you’ll lose partial data. Porter MCP enforces this limit at the platform level with automatic connection pooling.

• Restrict message searches to 20 per minute. The Search Messages endpoint enforces a limit of 20 searches per minute, with a mandatory 60-second cooldown after the first request in a bursted window (Mailchimp Release Notes). Ignoring this will lock you out of message-level data for at least 60 seconds. Porter spaces out search queries automatically to respect this window.

• Keep total groups (interests) under 60 per audience. Mailchimp’s API enforces a maximum of 60 groups per audience/list; exceeding this causes API write failures and segmentation errors (Cazoomi Support, Mailchimp Audience 60 Groups API Limitation). If Claude automates audience segmentation without this guardrail, you’ll hit a hard ceiling and break downstream automations. Porter validates group counts before any API write operation.

• Set API call timeouts under 120 seconds. Mailchimp’s API can experience latency during peak hours; long-hanging requests without timeouts can exhaust your concurrent connection pool and cascade into 429 errors across all active scripts. Set explicit timeouts in any Claude-generated code and implement exponential backoff for retries.

• Configure no more than 20 batch webhooks. The batch operations endpoint is the safest way to pull large datasets, but webhook-based batch notifications should be capped to avoid flooding your endpoint and creating retry loops. Use the async batch endpoint for bulk pulls rather than synchronous loops.

What Porter MCP does differently: it enforces these limits at the platform level. Porter’s Mailchimp MCP connector is read-only by default — it cannot send campaigns, modify audiences, or trigger Omnivore flags. It implements automatic rate limiting with exponential backoff, staying under the 10 concurrent connection cap and the 20 searches/minute threshold without user intervention. Per-account batching ensures that agencies managing multiple Mailchimp clients don’t accidentally burst across accounts. Scope minimization means Porter only requests the OAuth scopes required for metrics reading — never write permissions. That’s the behavior Mailchimp’s automated systems reward: predictable, low-volume, read-only API patterns that never trigger throttling, suspension, or abuse flags.

Frequently asked questions