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

Once connected, you can automate your Facebook Insights reporting and analysis — ask questions about your data, build dashboards, trigger alerts, or ship client-ready reports like the one below.

Connect Facebook Insights 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 Facebook Insights.

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 Facebook Insights 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 Facebook Insights:

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

1. Connect your Facebook Insights data to Porter

Porter sits between Meta’s Graph 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 Facebook profile. In Porter, click Create → pick Claude as the destination → select Facebook Insights as the source → sign in with Facebook to grant access to your Pages.

Select your Pages. Choose the Facebook Insights Pages you want Claude to query. When you select multiple Pages 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 Pages 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 Facebook Insights 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 Facebook Insights in plain English. Claude calls Porter behind the scenes, pulls live data from Meta, 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 (agencies, brand teams, creators & DTC, cross-channel), jump to the prompts section below.

Alternative ways to connect Facebook Insights 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 Facebook Insights data in front of Claude. The most common alternatives are Facebook Insights’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.

• 🔌 Facebook Insights’s direct API (or official MCP) — Talk to Meta’s Graph API yourself, or install Facebook Insights’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 Pages or agencies running multi-Page analysis. BigQuery aggregates; Claude only queries pre-built summaries.

Via Facebook Insights’s direct API (or official MCP)

If you’re building a product around Facebook Insights — or you’re a developer who’d rather own every layer of the integration — the most direct path is talking to Meta’s Graph API yourself, or installing the official Facebook Insights MCP (if one exists). Meta doesn’t ship an official MCP for Facebook Insights yet, so this means writing API calls directly in Claude Code or in your own scripts. You’ll need to follow Meta’s rate limits & quotas and request a Developer Token / API access where applicable. Either way, you skip Porter entirely and call Meta 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 Facebook Insights into a Sheet, then let Claude read the Sheet. You can automate the Facebook Insights → Sheets pipeline with Porter so it refreshes daily, or do one-off CSV exports from Facebook Insights’s native UI for static analysis.

Via Google BigQuery (for scale)

This is the path most people overlook — and it’s the one that saves you when your Facebook Insights Page gets serious. A single large Page or an agency managing 10+ Pages 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 Facebook Insights 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 Facebook Insights data, you let BigQuery aggregate into small, optimized tables, and Claude only queries the summarized output. Scale problem solved.

Connecting Facebook Insights 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 Facebook Insights 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 Facebook Insights, a whole category of work becomes possible.

What Claude Code unlocks that Claude alone cannot

Use cases — what you can actually do once Facebook Insights 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 Facebook Insights 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 Facebook Page Insights check-in. But chat is table stakes — the interesting use cases come next.

2. Blend Facebook Insights with your sales data (Meta Ads, Shopify, HubSpot)

This is where a 360° view gets real. When you connect Facebook Insights and your revenue source (Meta Ads for paid social amplification, Shopify for e-commerce conversion tracking, and HubSpot for lead nurturing), Claude can map Page posts and Reels to actual qualified leads or purchases — using post dates, campaign names, and UTM parameters — and give you content-to-revenue attribution that no platform-side number can.

Claude handles the post dates and UTM mapping and joins. You get a client-ready content-to-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 Facebook Insights 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 Looker Studio dashboard link — 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.

Facebook Insights 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 277 Facebook Insights fields and metrics across every reporting level from Page totals down to individual posts, Reels, videos, and reviews, plus breakdowns by City, Country, age, gender, post type, and hour of day. And the same MCP URL also unlocks 25+ other sources — so Claude can blend Facebook Insights with Google Ads, GA4, Shopify, HubSpot and more in a single prompt.

Date

MonthWeekYearMonth and yearWeek and yearDateDay of week (Mon – Sun)Hour of day

page

Page likesPage likes agePage likes genderPage followers agePage followers genderPage total followersPage actions: AngerPage actions: Haha

post

Post engagementsLikes churn rateLikes growth rateNet likes growthNonViralReachPercOrganicReachPercPage engagement rate (Impressions)Page engagement rate (Reach)

post_insights

Post actions: AngerPost actions: HahaPost actions: LikePost actions: LovePost actions: SadPost actions: WowPost ClicksTotal impressions of posts

reel

Reel backdated timeReel backdated time granularityReel blue reels play countReel content categoryReel creation timeReel viewsReel descriptionReel embeddable

video

Video backdated timeVideo backdated time granularityVideo content categoryVideo created time of dayVideo descriptionVideo embed htmlVideo embeddableVideo ID

Breakdown

CityConsumption typeCountry codeCountry iconCountry icon urlCountry nameCrosspost statusFeedback type

review

Review created dateHas review ratingHas reviewRecommendation typeReview ratingReview textReviewer nameReviewer id

post_attachments

Post descriptionPost Image URLShared post linkPost namePost Type String

page_info

Page IDPage namePage profile picturePage profile picture url

End date

End dateEnd time

Real time API

Real time

Start date

Start date

For the complete data dictionary, see All Facebook Insights fields and metrics.

Prompts you can copy-paste today

1. For agencies

Best for social media managers and marketing coordinators running multi-client Page reporting.

*”Show me my top 5 posts by Post engagements last 30 days in a ranked table.”* *”Compare my Organic reach this month versus last month and highlight the change.”* *”Why did my Page total impressions drop yesterday? Pull the breakdown by Hour of day.”* *”Draft a weekly client report using my Page engagement rate (Reach) from last 7 days.”*

2. For brand teams

Best for brand teams monitoring brand health, sentiment, and content theme performance over time.

*”Flag any post where my Post engagement rate fell more than 20 percent this quarter.”* *”How does my Organic reach of posts compare to my Paid reach of posts this week?”* *”Which Country gives me the highest Page engagement rate (Impressions) but lowest Page new likes last month?”* *”Cross-reference my top posts by Total reach of posts with my Reel views from last 14 days.”*

3. For creators & DTC

Best for content creators monetizing videos through ad breaks and DTC brands tracking Reel and video performance.

*”List my worst performing videos by Page video views last 60 days with their Video length.”* *”Project my Page new followers for next month based on the last 3 months trend.”* *”Alert me when my Page video watch 30s rate drops below 15 percent this month.”* *”Compare my Reel post video view time this week versus last week in a simple chart.”*

4. Cross-channel

Best for teams blending Facebook Insights with other marketing and revenue sources.

*”Cross-reference my Facebook Page total reach with Google Analytics 4 sessions last 30 days.”* *”Why did my Post reactions spike on Tuesday? Pull my Post shares and Post comments count too.”* *”Which City has the highest Page consumptions unique but lowest Page new unique likes this month?”* *”Draft a monthly summary for my team using my Organic reach and Page engagement rate (Reach).”*

Limits, auth, and best practices for Facebook Insights via Claude

*”We were pulling Page Insights for 50 pages in parallel and suddenly started getting error code 80006 — API calls were throttled. It took us 2 hours to figure out we were hitting the per-user rate limit because we didn’t implement exponential backoff.”* — Stack Overflow developer discussion on Meta Graph API throttling, 2024

This is the most common “horror story” with Facebook Insights API: not a ban, but a silent throttle that breaks your reporting pipeline. A marketing agency running weekly client reports across dozens of Pages is especially vulnerable. The real cost isn’t account suspension — it’s the 2–4 hour delay while you diagnose why your “automated” dashboard suddenly shows stale data, plus the manual rework to re-run queries with proper pacing. Unlike Meta Ads (where bad automation can trigger permanent bans), Facebook Insights is read-only — Meta’s enforcement model throttles aggressively but rarely suspends.

Meta’s rate limiting is quota-based and pattern-based, not tool-based. Meta doesn’t throttle accounts because you used Claude or an MCP. It throttles because of how the API was used: bursty parallel requests, missing pagination, or exceeding per-user/per-app call ceilings. Read-only Page Insights queries with proper pacing, batching, and backoff are safe. Parallel bursts across dozens of Pages without rate-limit handling are not.

The three patterns that lead to inaccurate Facebook Insights reports

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

1. Parallel API bursts across multiple Pages. Firing simultaneous requests to fetch Insights for 10+ Pages from the same app/user token triggers Meta’s Abuse Prevention Rate Limits (error code 80006 or 17xx series). Meta’s systems flag this as “bursty traffic” even if each individual call is legitimate. The result is not a ban — it’s throttling that returns `error_subcode: 2446079` and forces a cooldown period. Source: Meta Graph API Rate Limiting docs — “We throttle an application or user when either reaches a rate limit.” Instead, serialize requests or use batching with a maximum of 50 IDs per call.

2. Ignoring pagination and batching limits. Requesting all 277 metrics for a full 2-year date range in a single API call returns incomplete or estimated data. Meta’s Insights API paginates large result sets, and unbatched requests count heavily against your quota. A single unbatched “get everything” call can consume 10–20% of your hourly 200-call budget. Source: Meta Graph API Best Practices — “Use batch requests to reduce the number of HTTP connections.” Instead, paginate by date range (7-day windows) and batch metric requests.

3. Requesting excessive breakdowns in a single query. Adding multiple `breakdowns` (e.g., age + gender + city + country + hour) to a single Insights call multiplies the data volume and triggers throttling at lower call volumes. Meta’s systems estimate metrics when the underlying data becomes too granular, leading to inaccurate aggregations that look correct but aren’t. Source: Meta Marketing API Insights — Estimated Metrics — “Some metrics may be estimated when data is unavailable or incomplete.” Instead, request one breakdown dimension per query and blend results in your analysis layer (e.g., Claude with Porter MCP).

All three behaviors trigger quota throttling or data quality degradation. If you want to use Claude for Facebook Insights safely, pace your requests, batch intelligently, and limit breakdowns to one dimension per query.

The 5-rule scaling protocol

Based on Meta’s documented rate limits and the behaviors that have actually caused pipeline failures — not guesswork:

• Cap Graph API calls at 200 per hour per user. Meta’s Platform Rate Limit allocates ~200 calls/hour per user per app for Page Insights queries. Exceeding this triggers throttling for that user while the app’s total pool remains unaffected. Source: Meta Graph API Rate Limiting If you ignore this, your MCP session will stall mid-conversation while Claude waits for API responses that Meta is delaying.

• Cap Marketing API calls at your Business Use Case (BUC) tier. For Standard Access: 5,000 + 40 × Number of Active Custom Audiences per hour per ad account. For Advanced Access: 190,000 + 40 × Number of Active Custom Audiences per hour per ad account. Source: Meta Marketing API BUC Rate Limits If you ignore this, your automated reporting workflows will fail silently with error code 80004.

• Batch requests with a maximum of 50 IDs per call. Meta supports batching multiple object IDs into a single HTTP request, but exceeding 50 IDs per batch causes the request to fail or be partially processed. Source: Meta Graph API Batch Requests If you ignore this, you’ll waste quota on failed calls and get incomplete data back.

• Implement exponential backoff with the `Retry-After` header. When throttled (HTTP 429 or error code 80006), Meta returns a `Retry-After` header indicating seconds to wait. A proper backoff starts at 2 seconds and doubles on each retry (2s → 4s → 8s → 16s). Source: Meta Graph API Error Handling If you ignore this, your code will hammer Meta’s servers and extend the throttle window from minutes to hours.

• Limit breakdown dimensions to one per query and use 7-day date windows. Meta estimates metrics when breakdowns are too granular or date ranges exceed available raw data. Requesting `age,gender` together in one call with a 90-day range returns estimated values that don’t sum to the unbroken total. Source: Meta Marketing API Insights Best Practices If you ignore this, Claude will analyze “accurate-looking” data that is actually Meta’s statistical estimation — leading to incorrect conclusions about your audience.

What Porter MCP does differently: it enforces these rate limits and safeguards at the platform level. Porter’s Facebook Insights MCP connector is read-only by default — it never writes to your Page, eliminating the abuse vectors that trigger Meta’s strictest enforcement. The platform implements automatic exponential backoff with `Retry-After` header parsing, so throttling never breaks your Claude conversation. Requests are batched internally (respecting the 50-ID limit) and paced across time windows to stay well under the 200 calls/hour/user ceiling. Breakdowns are pre-configured into sensible defaults (e.g., one dimension at a time) so you get raw, non-estimated metrics rather than statistically blended data. That’s the behavior Meta’s automated systems handle gracefully — read-only, paced, batched, and scoped to `read_insights` + `pages_read_engagement` only.

Frequently asked questions