To connect Klaviyo to ChatGPT:
- Sign up free at portermetrics.com and connect your Klaviyo account with your Klaviyo account.
- In ChatGPT, click + → Connectors → Manage connectors → Add custom connector, name it Porter, paste
https://mcp.portermetrics.com/mcp, then click Add and authenticate with Google.
That’s it, you’re connected. Porter’s free plan covers up to 3 Klaviyo accounts with no usage limits on ChatGPT’s free plan. No credit card required.
What makes Porter different:
- 84+ Klaviyo metrics and dimensions across every reporting level in one connection.
- Universal Klaviyo MCP. Multi-source dashboards and blended metrics, competitor tracking with creative analysis, and automated alerts across 20+ marketing platforms. Your whole Klaviyo operation runs from one chat.
Prerequisites
- A Porter Metrics account with your Klaviyo account connected (free tier is enough to try it end-to-end)
- A ChatGPT account — the free plan works for ChatGPT Web; a Pro subscription is needed for Codex and Desktop MCP features
- Admin or standard access to the Klaviyo accounts you want to connect
Connect Klaviyo to ChatGPT 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 Klaviyo.
MCP (Model Context Protocol) is the open standard that lets AI tools like Claude, ChatGPT, Codex and others access and use external APIs — the things that make tools like Klaviyo 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.
The full setup takes under 5 minutes and breaks into three moves: connect Klaviyo to Porter, point ChatGPT at the Porter MCP, and ask your first question.
1. Connect your Klaviyo data to Porter
Porter sits between Klaviyo’s API and ChatGPT. It handles OAuth, rate limiting, pagination and all the plumbing so ChatGPT 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 Klaviyo. In Porter, click Create → pick ChatGPT as the destination → select Klaviyo as the source → sign in with Klaviyo to grant access to your accounts.
Select your accounts. Choose the Klaviyo accounts you want ChatGPT to query. When you select multiple accounts 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 accounts with large data volumes. This keeps ChatGPT’s responses fast even at scale.
2. Connect the MCP to ChatGPT
Porter’s MCP URL is what you paste into ChatGPT. Once added, ChatGPT can query Klaviyo data on demand in any conversation.
Go to chatgpt.com 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. ChatGPT 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 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 ChatGPT chat and ask anything about your Klaviyo in plain English. ChatGPT calls Porter behind the scenes, pulls live data from Klaviyo, 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, segmentation, agency, e-commerce, B2B, cross-channel), jump to the prompts section below.
Alternative ways to connect Klaviyo to ChatGPT
Porter MCP is the path we just walked through and the one we recommend for most marketers. It is not the only way to get Klaviyo data in front of ChatGPT, though. The most common alternatives are Klaviyo’s official MCP, a live Google Sheets bridge or CSV upload, and BigQuery for scale. Each has trade-offs, so pick the one that fits how your team already works.
- verified Klaviyo’s official MCP — Klaviyo launched its own first-party MCP server in GA on August 20, 2025. Verified via official Klaviyo newsroom. It authenticates with OAuth and is free for any Klaviyo customer. Klaviyo data only: no blends, dashboards, or multi-account setup.
- 📊 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 accounts or agencies running multi-account analysis. BigQuery aggregates; ChatGPT only queries pre-built summaries.
Via the Porter Metrics app in the ChatGPT marketplace
If you’d rather not paste a connector URL, install Porter straight from ChatGPT’s app gallery — it’s the same Porter connection behind the scenes, published as an approved ChatGPT app:
- Open the Porter Metrics app page in ChatGPT (or search “Porter Metrics” in the apps gallery).
- Click Connect and sign in with the same account you use in Porter.
- Authorize it and ask your first Klaviyo question — same live data as the MCP.
The trade-off to know: the marketplace app only updates after each ChatGPT review cycle, while the MCP updates the moment Porter ships. If you want every new tool and data source immediately, use the MCP; if you want the one-click install and don’t mind waiting for new features, the marketplace app is the shortest path — including write actions through your connected Porter account.
Via Klaviyo’s official MCP
Klaviyo launched its own first-party MCP server in General Availability on August 20, 2025. Source: Klaviyo Newsroom. The endpoint is https://mcp.klaviyo.com/mcp — setup reportedly via Claude Settings → Connectors → Browse Connectors → search “Klaviyo”, or add as custom remote MCP server. Auth is OAuth with dynamic client registration . The server offers ~16 tools covering profiles, lists, segments, campaigns, flows, and analytics data . Pricing is free for any Klaviyo customer .
The nuances: The official Klaviyo MCP only exposes Klaviyo data — no cross-platform blending. It does not support multi-account aggregation in a single query (appears scoped to a single Klaviyo account). It requires the user to manage auth lifecycle within their AI assistant. There are no dashboards, charts, or scheduled reporting built in — it is a data access layer only. No documented user-reported limitations were found as of June 2026, which may indicate the MCP is too new for widespread real-world feedback.
Porter MCP covers this out of the box: multi-source dashboards and blended metrics across 20+ platforms, multi-account aggregation, managed OAuth refresh and token expiry, built-in visualization and scheduled report delivery — on top of the same Klaviyo data.
When this makes sense: Teams that only use Klaviyo and want a first-party, officially supported connection without third-party intermediaries. For marketers who need cross-channel analysis or manage multiple brands, Porter MCP is the better fit.
Via Google Sheets (live Sheet or manual CSV)
If your team already lives in Google Sheets — or you want a paper trail before ChatGPT touches anything — feed Klaviyo into a Sheet, then let ChatGPT read the Sheet. You can automate the Klaviyo → Sheets pipeline with Porter so it refreshes daily, or do one-off CSV exports from Klaviyo’s native UI for static analysis.
The trade-off to know. With the MCP path, ChatGPT calls Klaviyo’s API directly and Klaviyo does the filtering and aggregation on its side — clean and deterministic. With the Sheets path, ChatGPT aggregates inside the Sheet itself, which can introduce hallucinations on totals, averages, and joins when you have thousands of rows. The upside is speed: for very large date ranges or historical analysis, a pre-built Sheet is dramatically faster than live API calls.
When this makes sense: finance teams that want to review numbers before ChatGPT acts on them, agencies already delivering client reports in Sheets, historical analysis across years of data, or any case where you care more about speed than real-time freshness.
Via Google BigQuery (for scale)
This is the path most people overlook — and it’s the one that saves you when your Klaviyo account gets serious. A single large marketer or an agency managing 10+ accounts will hit API rate limits and latency problems querying ChatGPT directly. ChatGPT will literally tell you it’s taking too long or timing out on big pulls.
BigQuery fixes that. You load Klaviyo data into BigQuery tables on a schedule, then connect BigQuery to ChatGPT — either through a BigQuery MCP or via Codex with SQL queries. Instead of asking ChatGPT to pull raw Klaviyo data, you let BigQuery aggregate into small, optimized tables, and ChatGPT only queries the summarized output. Scale problem solved.
When this makes sense: enterprise accounts with thousands of profiles/campaigns, agencies running multi-account analysis across 10+ clients, or any team already using BigQuery as a data warehouse. Porter loads Klaviyo (and 25+ other sources) directly into BigQuery so you don’t have to build your own ETL.
Read the full BigQuery tutorial →
Connecting Klaviyo to Codex
Most marketers lump ChatGPT and Codex 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 Klaviyo data seriously.
ChatGPT is a chat interface. You ask a question, ChatGPT 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.
Codex is ChatGPT 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 Klaviyo, a whole category of work becomes possible.
What Codex unlocks that ChatGPT alone cannot
This is where the MCP ecosystem pays off most. Because Codex 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.
Feed Codex your Klaviyo targets and goals — open rates, click rates, conversion rates — and ask it to generate a custom performance 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.
Combine your own Klaviyo performance from Porter with competitor email campaigns scraped via Firecrawl. Codex stitches both into a weekly competitive intelligence report — your numbers next to their subject lines and send timing, 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.
Use Airtable or Notion as the schema, Porter as the data source. Codex keeps every page populated with current open rate, click rate, and conversion rate for every account — 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.
A Codex routine on cron pulls Klaviyo via Porter, evaluates thresholds — open rate drops below 15%, unsubscribe rate spikes above 2% — 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: ChatGPT is for quick questions and ad-hoc dashboards. Codex 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 Klaviyo is connected to ChatGPT
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 Klaviyo 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 ChatGPT, ask a question, get an answer grounded in live data.
It’s the fastest way to replace a daily Klaviyo dashboard check-in. But chat is table stakes — the interesting use cases come next.
2. Blend Klaviyo with your revenue data (Shopify, Stripe, HubSpot)
This is where a 360° view gets real. When you connect Klaviyo and your revenue source (Shopify for e-commerce, Stripe for payments, HubSpot for CRM), ChatGPT can map email campaigns to actual purchases — using campaign names, timestamps, and profile IDs — and give you attribution that no platform-side number can.
ChatGPT handles the campaign names, timestamps, and profile IDs mapping and joins. You get a client-ready attribution report that no single platform can generate on its own.
3. Automated alerts and notifications on Slack or Gmail
With Codex you can turn Klaviyo 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 Codex 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 Klaviyo dashboard link — and you spend an hour explaining a broken dashboard. With ChatGPT 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.
Klaviyo fields and metrics you can query with ChatGPT
Before you start writing prompts, it helps to know what data is actually available. Porter MCP gives ChatGPT access to 84 Klaviyo fields and metrics across every reporting level, plus breakdowns by date, day of week, hour, month, quarter. And the same MCP URL also unlocks 25+ other sources — so ChatGPT can blend Klaviyo with Google Ads, GA4, Shopify, HubSpot and more in a single prompt.
Prompts you can copy-paste today
These prompts are organized by job: performance checks, segmentation & lists, agency workflows, DTC & e-commerce, B2B marketers, and cross-channel blends.
1. Performance checks
For quick status checks and trend spotting without opening the Klaviyo dashboard.
2. Segmentation & lists
For understanding your audience composition and targeting precision.
3. For agencies
For multi-client reporting and competitive benchmarking.
4. For DTC & e-commerce
For revenue-focused email and SMS optimization.
5. For B2B marketers
For lead nurturing and CRM-aligned email strategy.
6. Cross-channel
For blending Klaviyo with other marketing and sales platforms.
Limits, safety, and best practices for Klaviyo via ChatGPT
This post illustrates the most severe enforcement action Klaviyo takes: compliance-driven account suspension after a new user uploaded a list and sent their first campaign. While this is an email deliverability/compliance issue rather than an API abuse case, it demonstrates that Klaviyo’s automated systems do enforce hard limits when data quality or permissioning is suspect. For marketers using Klaviyo via Claude, the parallel risk is not “getting banned for MCP usage” but rather hitting rate ceilings mid-analysis and losing access to live data precisely when making time-sensitive campaign decisions. The cost is measured in interrupted workflow and delayed insights, not irreversible account loss.
A second documented frustration comes from developers whose integrations broke when Klaviyo changed API limits without warning: “API limits changed again” — Klaviyo Developer Community. This underscores that Klaviyo’s rate limits are living thresholds that can shift, making hard-coded assumptions dangerous.
Klaviyo’s rate-limit enforcement is quota-based and tiered by endpoint, not tool-based. Klaviyo does not ban or throttle accounts because you used Claude or an MCP server. It throttles because of how the API was used: exceeding the per-endpoint burst (per-second) or steady (per-minute) request thresholds triggers HTTP 429 responses with a Retry-After header. Read-only queries within your account’s tier are safe. Bursty parallel requests, write operations at scale, or mixing high-volume endpoints without awareness of their respective tiers are not. The system uses a fixed-window algorithm, meaning counters reset at predictable intervals rather than sliding windows.
The two ways to burn through your Klaviyo quota
After reviewing official docs and community threads, two patterns come up again and again.
1. Parallel API bursts across multiple endpoints. Sending concurrent requests to several Klaviyo endpoints simultaneously (e.g., querying campaigns, flows, segments, and metrics at once via Claude) can exceed the per-account burst limit of 1 request per second for Tier XS endpoints or 3 requests per second for Tier S endpoints like metrics. This triggers 429 throttling and forces the MCP server to back off, leaving the user with partial or stale data. Klaviyo Developer Community — Rate Limits Discussion
2. Exceeding endpoint-specific steady limits. Klaviyo assigns each endpoint to a tier with distinct burst and steady thresholds. For example, Tier S endpoints allow 60 requests per minute steady after the initial burst. A marketer asking Claude to “pull every campaign from the last 12 months with full event breakdown” can unknowingly burn through this quota in a single conversation thread. The result is not a ban but a hard stop on data access until the window resets. Klaviyo API Overview — Rate Limit Tiers
Both behaviors trigger rate throttling (HTTP 429). If you want to use ChatGPT for Klaviyo safely, pace your queries and let Porter’s MCP handle batching automatically.
The 5-rule scaling protocol
Based on Klaviyo’s documented rate limits and the behaviors that have actually caused throttling — not guesswork:
-
Use private API keys exclusively for
/apiendpoints. Public keys are restricted to/clientendpoints only; all MCP server queries route through/apiand require a private key. Misconfiguration triggers immediate 400/401 errors. Klaviyo Help Center — API Keys -
Respect the 3-requests-per-second burst limit for Tier S endpoints (metrics, campaigns, flows). Tier S is the most common tier for marketing analytics endpoints. Exceeding 3 req/s burst triggers 429 throttling. Klaviyo Developer Community — Rate Limits
-
Stay under the 60-requests-per-minute steady limit for Tier S endpoints. After the initial burst window, sustained querying must remain below 60 req/min. For large historical pulls, paginate with
page_cursorand pause between batches. Klaviyo API Overview — Rate Limit Tiers -
Honor the
Retry-Afterheader on 429 responses. Klaviyo’s documentation states that 429 errors include aRetry-Afterheader indicating seconds to wait. Ignoring this and immediately retrying extends the throttle window. -
Grant only the minimum scopes required in Klaviyo API Key settings. The MCP server only needs read access to Campaigns, Flows, Segments, and Metrics. Write scopes (e.g.,
campaigns:write,profiles:write) should remain disabled unless actively managing campaigns via Claude.
What Porter MCP does differently: it enforces these rate limits and safeguards at the platform level. Porter’s Universal MCP server implements read-only by default for all Klaviyo queries, eliminating the risk of accidental write operations. It applies automatic request batching and backoff when Klaviyo returns 429 responses, transparently retrying with exponential delay so the marketer never sees a broken conversation. Per-account connection isolation ensures that one user’s burst traffic never bleeds into another’s quota. That’s the behavior Klaviyo’s automated systems handle gracefully and do not flag.
Frequently asked questions
Ready to chat with your Klaviyo?
Open ChatGPT, add the Porter connector, and ask your first question. If you don’t have Porter yet, start a free trial and connect your Klaviyo account — you’ll be chatting with your campaigns in under five minutes.
rocket_launchStart free Porter trialopen_in_newOpen ChatGPT