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

Prerequisites

• A Porter Metrics account with your Pinterest Ads 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 Pinterest Ads ad accounts you want to connect

Connect Pinterest Ads 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 Pinterest Ads.

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 Pinterest Ads 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 Pinterest Ads to Porter, point Claude at the Porter MCP, and ask your first question.

1. Connect your Pinterest Ads data to Porter

Porter sits between Pinterest’s Ads API v5 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 Pinterest Ads account. In Porter, click Create → pick Claude as the destination → select Pinterest Ads as the source → sign in with Pinterest to grant access to your ad accounts.

Select your ad accounts. Choose the Pinterest Ads ad accounts you want Claude to query. When you select multiple ad 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 ad accounts 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 Pinterest Ads 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 Pinterest Ads in plain English. Claude calls Porter behind the scenes, pulls live data from Pinterest, 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 Pinterest Ads 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 Pinterest Ads data in front of Claude. The most common alternatives are Pinterest Ads’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.

• 🔌 Pinterest Ads’s direct API (or official MCP) — Talk to Pinterest’s Ads API v5 yourself, or install Pinterest Ads’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 ad accounts or agencies running multi-ad account analysis. BigQuery aggregates; Claude only queries pre-built summaries.

Via Pinterest Ads’s direct API (or official MCP)

If you’re building a product around Pinterest Ads — or you’re a developer who’d rather own every layer of the integration — the most direct path is talking to Pinterest’s Ads API v5 yourself, or installing the official Pinterest Ads MCP (if one exists). Pinterest 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 Pinterest’s rate limits & quotas and request a Developer Token / API access where applicable. Either way, you skip Porter entirely and call Pinterest 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 Pinterest Ads into a Sheet, then let Claude read the Sheet. You can automate the Pinterest Ads → Sheets pipeline with Porter so it refreshes daily, or do one-off CSV exports from Pinterest Ads Manager 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 Pinterest Ads ad account gets serious. A single large advertiser or an agency managing 10+ ad accounts 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 Pinterest Ads 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 Pinterest Ads 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 Pinterest Ads 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 Pinterest Ads 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 Pinterest Ads, 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 budget management app Stack: Porter MCP + Vercel MCP (or Cloudflare Pages, Netlify) Feed Claude Code your Pinterest Ads targets and goals — CPA goals, daily budgets, ROAS thresholds — and ask it to generate a custom 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 Pinterest Ads performance from Porter with competitor landing pages and live ads from the Meta Ad Library scraped via Firecrawl. Claude Code stitches both into a weekly competitive intelligence report — your numbers next to their creative angles and pricing, 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 spend, CPA, and ROAS for every ad 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.

🔔 24/7 alerts on spend, CTR, and quality drops Stack: Porter MCP + Slack MCP (or Gmail MCP) A Claude Code routine on cron pulls Pinterest Ads via Porter, evaluates thresholds — CTR drops below 1%, daily spend spikes 2× the trailing average — 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 Pinterest Ads 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 Pinterest Ads 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 Pinterest Ads Manager check-in. But chat is table stakes — the interesting use cases come next.

2. Blend Pinterest Ads with your sales data (Stripe, HubSpot, Shopify)

This is where a 360° view gets real. When you connect Pinterest Ads and your revenue source (Stripe for SaaS, HubSpot CRM for B2B, Shopify for e-commerce), Claude can map ad campaigns to actual closed-won deals or purchases — using UTMs, campaign names, and timestamps — and give you attribution that no platform-side number can.

Claude handles the UTMs, campaign names, and timestamps 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 Claude Code you can turn Pinterest Ads 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 Data Studio link, Looker breaks, the client panics — and you spend an hour explaining a broken dashboard. 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.

Pinterest Ads fields and metrics you can query with Claude

Time

Date

Geography

Account CountryCatalog Location

Visibility

Ad Groups Tracking Urls ImpressionCampaigns Tracking Urls ImpressionConfigs Md FrequencyImpressionsImpression 1 GrossImpressions 2Ad User Lifetime FrequencyImpression

Engagement

Ad Click Tracking URLClickthrough 1Clickthrough 1 GrossClickthrough 2Click-through rateEngagement RateEngagement Rate 1Engagement Rate 2

Conversion

ROASConversion Learning Mode TypeConversion TagConversion Tags NameConversion Tags StatusCost Per In-app checkuotAd Form IdOptimization Attribution Window Days

Cost & Bidding

keyword Matching BidAd Group Bid AmountAd Group Bid StrategyAd Group BudgetAd Group Budget TypeCPCCPMCpm In Micro Dollar

Campaign

Camping Daily BudgetCampaing StatusCampaign IdCampaign BudgetCampaign Name

Ad

Ad Group StatusAd Group IdAd Groups Created TimeAd Group End TimeAd Groups NameAd Group Start TimeAd Groups StatusAd Groups Type

Creative

Pin TypePin Title

Audience

Audience TypeAudience DescriptionsAudiences IdAudiences NameAudiences StatusAudiences Type

Placement & Device

Ad Group Placement GroupAd Group Traffic Target Type

Product & Catalog

Catalog TypePin Product Tags

Profile & Contact

Customer Lists Created TimeCustomer Lists IdCustomer Lists NameCustomer Lists StatusCustomer Lists TypeCustomer Lists Updated Time

Keywords & Search

Keyword IdKeyword Typekeyword Matching Type

URLs & Links

Ad Destination URLPin URLEvent Tracking Urls Audience VerificationEvent Tracking Urls Buyable Button

Status & Lifecycle

Ad StatusKeyword ArchivedAd Group Auto Targeting EnabledCampaigns StatusCatalog StatusCatalog Product Group StatusConversion Tags Double Click Integration is EnableConfigs Aem Enabled

IDs & Identifiers

Account IdAdvertiser IdBoard IdBoard Pins IdBoard Sections IdCatalog IdCatalog IdCatalogs Porduct Group Id

Other

Account Created TimeAccount NameAccount Owner NameAccount Updated TimeAd NamePin TextAndroid Deep LinkAd Group Billed Event

User Account

Account AboutAccount Follower CountAccount Pin CountAccount TypeAccount Board CountAccount Business NameAccount Following CountAccount Monthly Views

Pins

Pin Image

Prompts you can copy-paste today

1. For agencies

Use these when managing multiple client Pinterest Ads accounts or building white-label reports.

2. For B2B marketers

Use these when tracking lead generation, signups, and cost-per-lead from Pinterest Ads.

3. For e-commerce teams

Use these when optimizing Shopping Ads, catalog performance, and checkout value.

4. Cross-channel

Use these when blending Pinterest Ads with other marketing sources in one conversation.

Limits, safety, and best practices for Pinterest Ads via Claude

Pinterest’s API is not a “ban first” ecosystem. The most common real-world pain point marketers report is not account suspension—it’s quiet data degradation. As ad blockers, iOS privacy restrictions, and cookie deprecation reduce signal fidelity, conversion metrics in the API drift from ground truth. A marketer running Pinterest Shopping campaigns may see ROAS figures in the API that under-report actual checkout value by 15–30% compared to their Shopify backend, not because the API is broken, but because the signal path (pixel → server → API) is incomplete. The cost is not a banned account; it’s mis-allocated budget based on incomplete data.

Pinterest’s rate limiting is quota-based and category-specific, not tool-based. Pinterest does not ban or throttle accounts because you used Claude or an MCP connector. It throttles because of how the API was used: exceeding the 100 requests per second per user per app ceiling for standard API requests, or hitting category-specific write limits (e.g., ads_write scope for promotion updates). Read-only analytics access via OAuth is safe and expected. Bursty, high-frequency conversion event uploads and unbatched write operations are not. Staying within the standard request quota and using read-only scopes is handled gracefully. Parallel, unthrottled bursts across multiple apps or accounts are not.

The three patterns that lead to inaccurate Pinterest Ads reports

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

1. Unbatched, high-frequency conversion data sends. Sending conversion events in real-time or near-real-time without batching can trigger Pinterest’s Conversions API rate limits. When throttled, events are dropped or delayed, which silently degrades attribution accuracy. What to do instead: batch conversion events and implement exponential backoff when receiving HTTP 429 responses.

2. Relying on API-reported conversion data as ground truth without cross-checking. Pinterest Ads API conversion metrics are subject to signal loss from ad blockers, iOS 14.5+ privacy restrictions, and cookie deprecation. A campaign showing a 2.5x ROAS in the API may actually be at 1.8x when measured against first-party checkout data. This is not an API ban risk—it is a decision-quality risk. What to do instead: always reconcile Pinterest API conversion values with your e-commerce platform (Shopify, WooCommerce) or first-party analytics within a 24–48 hour window.

3. Exposing PII in API calls or third-party connectors. Pinterest’s API terms and brand-safety policies restrict how user data is handled. Passing raw email lists, phone numbers, or customer IDs through unvetted third-party tools can violate Pinterest’s data policies and trigger access review. What to do instead: use OAuth-based connectors that do not store or train on your data, and ensure any audience upload flows through Pinterest’s native Customer List API with hashed identifiers.

Both behaviors trigger throttling or data quality degradation, not bans. If you want to use Claude for Pinterest Ads safely, stay within read-only scopes, batch where needed, and cross-check conversion data against your first-party sources.

The 5-rule best-practice protocol

Based on Pinterest’s documented rate limits and quotas and the behaviors that have actually caused data degradation — not guesswork:

• Stay under the 100 req/s ceiling. Pinterest enforces a rate limit of 100 requests per second per user per app for standard API requests. Bursting above this threshold triggers HTTP 429 throttling, which delays or drops analytics requests. If you manage multiple ad accounts, the limit applies per app per user—not per account, so concurrent queries across accounts count toward the same quota. Consequence if ignored: incomplete metric pulls, stale dashboards, and missed optimization windows. How Porter enforces this: Porter MCP batches API requests and implements client-side rate limiting with automatic backoff.

• Batch conversion events; don’t stream them. Sending individual conversion events as they happen consumes quota rapidly and increases throttling risk. Consequence if ignored: dropped conversion events, degraded attribution, and inaccurate ROAS reporting. How Porter enforces this: Porter’s Pinterest connector uses read-only analytics scopes by default and does not send conversion events, eliminating this risk entirely for reporting use cases.

• Reconcile conversion data within 24–48 hours. Pinterest Ads API conversion metrics have a 24–48 hour latency for final attribution. Making budget decisions on same-day API data leads to over- or under-investment in campaigns. Consequence if ignored: budget misallocation based on incomplete attribution, especially for multi-touch conversion paths common in Pinterest’s discovery-driven funnel. How Porter enforces this: Porter surfaces data freshness timestamps in query responses so users know when metrics are provisional.

• Use read-only OAuth scopes by default. Pinterest’s API requires OAuth 2.0 authentication with scope-specific permissions. Granting write access (ads_write) when only reporting is needed increases the blast radius of any credential compromise. Consequence if ignored: accidental campaign modifications, budget changes, or ad pauses if tokens are mishandled. How Porter enforces this: Porter MCP requests minimum viable scopes—read-only analytics access by default. No write permissions are requested or stored.

• Never pass raw PII through third-party connectors. Pinterest’s brand safety and data policies require hashed or encrypted identifiers for audience data. Uploading unhashed email lists or customer data through intermediary tools violates platform policy. Consequence if ignored: access review, connector suspension, or advertiser account flagging for data handling violations. How Porter enforces this: Porter MCP does not store, cache, or train on customer data. All OAuth tokens are encrypted at rest and queries are ephemeral—no data persists in Porter’s infrastructure after the response is delivered.

What Porter MCP does differently: it enforces these safeguards at the platform level. Porter’s Pinterest Ads connector operates with read-only OAuth scopes by default, requests are client-side rate-limited with automatic backoff to stay within Pinterest’s 100 req/s quota, and no customer data is stored, cached, or used for model training. That’s the behavior Pinterest’s automated systems handle gracefully: predictable, read-only, within-quota traffic from a verified OAuth app.

Frequently asked questions