4 ways to connect TikTok Insights to Claude in 2026 (for free)
Porter Metrics+TikTok Insights+
boltTikTok Insights + AI Tutorial · 2026

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

Learn to connect TikTok Insights to Claude via MCP, Google Sheets, or BigQuery — no code required.

rocket_launchUse Porter for free14-day unlimited free trial. After that, keep unlimited queries for up to 3 pages and 30 days of historical data — no credit card required.
Juan Bello

Juan Bello

Founder, Porter Metrics · May 04, 2026 · 18 min read

Connect TikTok Insights to Claude — featured image
boltTL;DR

To connect TikTok Insights to Claude via MCP: copy mcp.portermetrics.com/mcp, go to Claude.ai, open Connectors → Manage connectors → Add custom connector, paste the URL, and sign in. From there, ask Claude anything about your TikTok Insights TikTok accounts in plain English.

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

TikTok Insights client dashboard built with Claude

Prerequisites

  • A Porter Metrics account with your TikTok Insights 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 TikTok Insights TikTok accounts you want to connect

Connect TikTok 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 TikTok 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 TikTok 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.

content_paste
Copy-paste setup
No tokens, no scripts, no developer help — literally paste one URL into Claude and you’re done.
hub
Works with every AI tool
Claude, Claude Code, ChatGPT, Cursor, Antigravity, Lovable, Vercel v0, Zapier. One MCP URL, every tool that speaks the protocol.
merge_type
20+ sources in one connection
Porter’s MCP ships TikTok Insights plus Google Ads, GA4, Shopify, HubSpot, Klaviyo, Google Sheets and 20+ more. Query and blend them all in a single conversation.
tune
Perfect granularity
Spreadsheets lock you into the columns you exported. MCP hits TikTok’s API directly — so you can filter by video, break down by date range or audience segment, and add new dimensions on the fly without rebuilding tables.

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

1. Connect your TikTok Insights data to Porter

Porter sits between TikTok’s Insights 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 TikTok Business account. In Porter, click Create → pick Claude as the destination → select TikTok Insights as the source → sign in with TikTok to grant access to your TikTok accounts.

Connect and authorize your TikTok Insights profile

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

Select TikTok Insights account

Optional: enable automatic BigQuery storage if you’re connecting multiple TikTok 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 TikTok Insights data on demand in any conversation.

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

Click the + icon in the Claude chat input

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

Hover Connectors and click Manage connectors

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

Click + at the top of the Connectors panel

Pick Add custom connector from the dropdown that appears.

Select Add custom connector from the dropdown

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

Type Porter in the connector name field

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

Paste the Porter MCP URL into the Remote MCP server field

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.

Click Add on the custom connector dialog

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

Porter read-only tools visible in the Claude connectors panel

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 TikTok Insights in plain English. Claude calls Porter behind the scenes, pulls live data from TikTok, and answers with tables, charts, or summaries.

Try one of these to verify the setup is working:

chat_bubble“What were my top 5 videos by Video Full Watched Rate last 30 days?”
chat_bubble“Compare my Profile Video Views this month vs last month.”
chat_bubble“Which of my videos with over 10k Video Views had the lowest Video Full Watched Rate last month?”

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 TikTok 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 TikTok Insights data in front of Claude. The most common alternatives are TikTok 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.

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

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

If you’re building a product around TikTok Insights — or you’re a developer who’d rather own every layer of the integration — the most direct path is talking to TikTok’s Insights API yourself. TikTok has not published an official MCP server as of 2025. You’ll need to follow TikTok’s rate limits & quotas and request a Developer Token / API access where applicable. Either way, you skip Porter entirely and call TikTok from your own code or from Claude Code with raw HTTP requests.

The trade-off to know. Going direct gives you maximum control and the freshest possible data — every endpoint, every parameter, no abstraction layer in between. But you’re now responsible for OAuth flows, refresh tokens, rate limits, pagination, schema changes, and error retries. And critically, you only get one source. The moment you also want Google Ads, GA4 or Shopify in the same conversation, you’re back to building (or stitching together) more integrations.
When this makes sense: engineering teams that need a single source with full control, products that ship TikTok Insights data as a feature (where you own the integration anyway), or one-off scripts where you don’t mind writing the auth and pagination code yourself. For marketers who want to ask questions in plain English and blend TikTok Insights with the rest of their stack in a single conversation, the Porter MCP path is dramatically less work.

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 TikTok Insights into a Sheet, then let Claude read the Sheet. You can automate the TikTok Insights → Sheets pipeline with Porter so it refreshes daily, or do one-off CSV exports from TikTok Insights’s native TikTok Analytics dashboard for static analysis.

The trade-off to know. With the MCP path, Claude calls TikTok’s API directly and TikTok does the filtering and aggregation on its side — clean and deterministic. With the Sheets path, Claude 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 Claude 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.

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 TikTok Insights TikTok account gets serious. A single large TikTok account or an agency managing 10+ TikTok 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 TikTok 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 TikTok Insights data, you let BigQuery aggregate into small, optimized tables, and Claude only queries the summarized output. Scale problem solved.

When this makes sense: enterprise TikTok accounts with millions of video views, agencies running multi-TikTok account analysis across 10+ clients, or any team already using BigQuery as a data warehouse. Porter loads TikTok Insights (and 25+ other sources) directly into BigQuery so you don’t have to build your own ETL.

Read the full BigQuery tutorial →

Connecting TikTok 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 TikTok 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 TikTok Insights, 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 TikTok performance dashboard Stack: Porter MCP + Vercel MCP (or Cloudflare Pages, Netlify) Feed Claude Code your TikTok Insights targets and goals — Video Full Watched Rate goals, post timing, and engagement thresholds — 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.

🔍 Full competitor + performance monitoring Stack: Porter MCP + Firecrawl MCP Combine your own TikTok Insights performance from Porter with competitor TikTok content and trending sounds scraped via Firecrawl. Claude Code stitches both into a weekly competitive intelligence report — your numbers next to their hook styles and posting cadence, 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 Video Views, Video Full Watched Rate, and Profile New Followers for every TikTok 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 engagement drops, viral spikes, and follower trends Stack: Porter MCP + Slack MCP (or Gmail MCP) A Claude Code routine on cron pulls TikTok Insights via Porter, evaluates thresholds — Video Full Watched Rate drops below 20%, daily Profile New Followers drops 50% below the trailing 7-day 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 TikTok 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 TikTok 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.

chat_bubble“Show me my top 5 videos by Video Full Watched Rate last 30 days.”
chat_bubble“Compare my Profile Video Views this month vs last month.”
chat_bubble“Flag any video where Video Views dropped more than 40% week over week.”

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

2. Blend TikTok Insights with your revenue data (Meta Ads, Shopify, HubSpot)

This is where a 360° view gets real. When you connect TikTok Insights and your revenue source (Meta Ads for paid social benchmarks, Shopify for e-commerce attribution, HubSpot for lead nurturing), Claude can map TikTok videos to actual purchases or sign-ups — using video URLs, campaign names, and timestamps — and give you attribution that no platform-side number can.

chat_bubble“Rank my TikTok videos by Video Website Clicks and show matching Shopify sales last 30 days.”
chat_bubble“Match my top TikTok videos by Video Views with my TikTok Ads spend to see which organic posts to boost.”

Claude handles the video URLs, 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 TikTok 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.

chat_bubble“Alert me when any video’s Video Shares jump over 200% in 24 hours.”
chat_bubble“Why did my Profile New Followers drop yesterday? Break it down by Hour.”

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 TikTok Analytics 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.

chat_bubble“Draft a weekly TikTok summary for my manager using last week’s Profile Video Views and Profile New Followers.”
chat_bubble“Build an HTML report of my top 10 videos by Video Website Clicks with thumbnails and captions.”

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.

TikTok 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 90 TikTok Insights fields and metrics across profile and video reporting levels, plus breakdowns by date, hour, day of week, month, quarter, week, year, year-month, year-quarter, and year-week. And the same MCP URL also unlocks 25+ other sources — so Claude can blend TikTok Insights with Google Ads, GA4, Shopify, HubSpot and more in a single prompt.

Metric
NumberNumberNumberNumberNumberNumberNumberNumber
Dimension
StringStringStringStringStringStringDateDate

Prompts you can copy-paste today

1. For agencies

Deliver client-ready reports that prove organic TikTok is moving the needle, without spending hours in CSV exports.

chat_bubble“Show me my top 5 videos by Video Full Watched Rate last 30 days.”
chat_bubble“Compare my Profile Video Views this month vs last month.”
chat_bubble“Flag any video where Video Views dropped more than 40% week over week.”
chat_bubble“Why did my Profile New Followers drop yesterday? Break it down by Hour.”

2. For brand teams

Validate brand positioning and audience fit using demographic and retention data, then package it for internal stakeholders.

chat_bubble“List my worst-performing videos by Video Average Time Watched last 14 days.”
chat_bubble“How do my Followers Age % compare between my top 3 and bottom 3 videos?”
chat_bubble“Which video length gets the highest Video Full Watched Rate in my last 20 posts?”
chat_bubble“Draft a weekly TikTok summary for my manager using last week’s Profile Video Views and Profile New Followers.”

3. For creators & DTC

Turn every video into a conversion experiment — optimize hooks, CTAs, and post timing to drive clicks and sales.

chat_bubble“Show me my top 10 videos by Video Website Clicks last 30 days.”
chat_bubble“Compare my Video Profile Views this week vs the same week last month.”
chat_bubble“Alert me when any video’s Video Shares jump over 200% in 24 hours.”
chat_bubble“Which of my videos with over 10k Video Views had the lowest Video Full Watched Rate last month?”

4. Cross-channel

Connect TikTok Organic performance to downstream business outcomes in other tools — paid, web, or sales.

chat_bubble“Rank my TikTok videos by Video Website Clicks and show matching Shopify sales last 30 days.”
chat_bubble“Compare my TikTok Profile Video Views this month with my Instagram video views last month.”
chat_bubble“Did my TikTok Video Website Clicks spike on days my Google Analytics 4 traffic jumped last month?”
chat_bubble“Match my top TikTok videos by Video Views with my TikTok Ads spend to see which organic posts to boost.”

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

chat_bubble“During the 2024 European elections, researchers relying on TikTok’s Research API reported significant data quality issues: missing posts, incomplete comment threads, and inconsistent search results that undermined their ability to track political discourse accurately.” — Tech Policy Press, <a href=”https://techpolicy.press/-researcher-data-access-under-the-dsa-lessons-from-tiktoks-api-issues-during-the-2024-european-elections”>Researcher Data Access Under the DSA: Lessons from TikTok’s API Issues</a>, 2024.”

This episode is the closest documented real-world cautionary tale involving TikTok data access at scale. It illustrates a risk profile that applies to marketers too: data completeness and freshness are not guaranteed, even when you are authenticated through official channels. A social media analyst building a weekly TikTok performance report for a D2C brand could unknowingly present incomplete follower-activity data to stakeholders if the API returns partial records during high-traffic windows. The cost is not a banned account — it is bad decisions made on incomplete data.

No documented cases exist (as of 2024–2026) of marketers receiving account bans, suspended Business access, or exhausted quotas specifically from using the TikTok Insights API. The platform’s enforcement model targets abusive data harvesting and credential-stuffing attacks, not legitimate read-only analytics usage.

TikTok’s automated enforcement is behavior-based and quota-based, not tool-based. TikTok does not ban or throttle accounts because you used Claude or an MCP server. It throttles or suspends API access because of how the API was used: high-volume concurrent requests from a single IP, browser-automation patterns that mimic bot traffic, or programmatic writes exploiting undocumented endpoints. Read-only access through the official TikTok for Business API, staying within documented request ceilings, and respecting OAuth token scopes is safe. Parallel bursts, scraping workarounds, and cross-endpoint quota abuse are not.

The two patterns that lead to inaccurate TikTok Insights reports

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

1. Parallel API bursts from a single session. Sending high-volume, concurrent requests from few IPs or sessions mimics bot-like patterns and triggers TikTok’s behavioral detection systems. This is the most common trigger for HTTP 429 (Too Many Requests) responses and potential temporary IP-level blocks. The official TikTok API v2 enforces a 600 requests per minute sliding-window limit; exceeding it results in throttling, not a platform ban, but it can stall your reporting pipeline during critical campaign windows.

2. Relying on unofficial scraping or reverse-engineered endpoints. Using browser automation, headless Chrome, or undocumented internal APIs to extract TikTok Insights data bypasses OAuth and Business Account authorization entirely. This violates TikTok’s Platform Terms and exposes the user to account suspension or legal action under the platform’s anti-scraping provisions. In 2025, security researchers documented attackers abusing TikTok and Instagram APIs for credential stuffing and data harvesting — the same detection signatures flag unauthorized scraping tools. Source: Security Boulevard, 2025. The safe alternative is to use the official TikTok for Business API with a verified Business or Creator account.

3. Ignoring data freshness windows and sampling thresholds. TikTok Insights data is not real-time; metrics like Profile Video Views and Follower Net Growth can lag by 24–48 hours . During viral spikes, the API may return sampled or cached values rather than live counts. A marketer who pulls “yesterday’s” Video Full Watched Rate and immediately adjusts ad spend based on that number risks optimizing toward stale data. The enforcement here is not a ban — it is silent data quality degradation that undermines decision-making.

Both behaviors trigger rate throttling and data quality degradation. If you want to use Claude for TikTok Insights safely, stick to the official API through Porter MCP, stay under request ceilings, and validate data freshness before acting on it.

The 5-rule accuracy protocol

Based on TikTok Insights’s documented rate limits and quotas and the behaviors that have actually caused inaccurate reports — not guesswork:

  • Stay under the 600 requests per minute ceiling. The general TikTok API v2 enforces a sliding-window limit of 600 requests per minute across endpoints such as /v2/user/info/, /v2/video/query/, and /v2/video/list/. Source: TikTok for Developers — API v2 Rate Limit. If you exceed this, TikTok returns HTTP 429 and may temporarily throttle your app ID. Porter MCP enforces this internally with request batching and exponential backoff, so you do not need to manage it manually.

  • Use only verified Business or Creator accounts. The TikTok Insights connector requires a TikTok Business Account with completed verification. Personal profiles and unverified accounts cannot authorize the app or return analytics data. . Attempting to pull data from an unauthorized account type returns empty datasets, not an error — which can lead to false conclusions.

  • Cache results and avoid redundant polling. . As a best practice, do not poll the same video or profile metrics more than once per hour unless you are tracking a live campaign. Repeated identical queries burn quota without improving data freshness. Porter MCP caches responses server-side to prevent redundant API calls.

  • Never expose OAuth tokens or Business Account credentials to third-party tools. TikTok’s OAuth flow issues scoped tokens that are tied to your specific app and Business Account. Sharing these tokens with unofficial “TikTok analytics” Chrome extensions or pasting them into public Claude conversations violates the principle of least privilege. If a token is leaked, revoke it immediately in the TikTok for Developers portal.

  • Validate data freshness before acting on it. TikTok Insights metrics can lag. Before making budget or content decisions based on API data, check the Date or Hour dimension returned in the response to confirm the record covers the expected window. If the most recent row is >24 hours old, flag it as stale rather than treating it as current performance. Porter surfaces the Date and Hour fields natively so Claude can reason about freshness explicitly.

What Porter MCP does differently: it enforces these safeguards at the platform level. Porter’s TikTok Insights connector is read-only by default — it cannot post, edit, or delete content, eliminating the entire class of write-based abuse triggers. It implements rate-limiting with exponential backoff aligned to TikTok’s documented 600 req/min ceiling, so your account never hits a 429. It uses per-account request batching to spread load across time windows rather than firing parallel bursts. It requests minimal OAuth scopes (only analytics read permissions, never content publishing or user messaging). That’s the behavior TikTok’s automated systems handle gracefully — and it’s why no Porter user has reported throttled or suspended access.

Frequently asked questions

Q: What is a TikTok Insights MCP?

A TikTok Insights MCP (Model Context Protocol) is an open standard that lets AI tools — Claude, Claude Code, ChatGPT, Cursor — connect to your TikTok Insights data without custom integrations. Porter’s MCP server makes your 90+ profile and video metrics available through one URL: no tokens, no scripts, no developer setup.

Q: What’s the difference between Claude and Claude Code?

Claude is the conversational product (web, app, mobile). Claude Code is a terminal-based developer tool that can write scripts, save files, and automate workflows. Both can connect to TikTok Insights via MCP.

Q: How fresh is the data? Is it real time?

No. TikTok’s API returns current totals at the time of each call, but new video data can take 24–48 hours to appear. . Porter MCP pulls live, so your data is always within that window.

Q: Are there rate limits for TikTok Insights data?

Yes. TikTok’s general API v2 enforces a 600 requests per minute sliding-window limit. . Porter MCP batches and caches requests automatically so you rarely hit them.

Q: Why do Claude’s numbers sometimes differ from TikTok Analytics dashboard?

Three common reasons: (1) Refresh lag — the API may return totals captured hours before the dashboard updated. (2) Sampling — during viral spikes, TikTok may serve cached or sampled values rather than live counts. (3) Aggregation window — the API returns cumulative totals at call time, while the dashboard can show filtered or segmented views. The fix: check the Date or Hour dimension in the API response before making budget decisions.

Q: Will using Claude affect my TikTok Insights access or limits?

No. TikTok doesn’t ban or restrict accounts for legitimate API usage, and Porter MCP is read-only by default — it stays well inside TikTok’s normal rate limits. The thing to watch is data completeness and freshness during high-traffic windows — see the limits section above.

Ready to chat with your TikTok Insights?

Open Claude, add the Porter connector, and ask your first question. If you don’t have Porter yet, start a free trial and connect your TikTok Insights account — you’ll be chatting with your TikTok accounts in under five minutes.

rocket_launchStart free Porter trialopen_in_newOpen Claude