Connect Polar MCP to your AI Agents

Ask your Polar revenue, subscriptions, and usage data anything — in plain English.

Example prompts

Everything you can ask your agent about your Polar data.

Ask in plain English — Sequel translates it into a Polar query, runs it, and your agent hands back the answer. No SQL, no dashboards, no CSV exports.

What you can ask your agent
  • What's our MRR trend over the last six months?
  • Which cancellation reason drove the most churn last quarter?
  • How much revenue did we make in March, net of refunds?
  • Which subscriptions are past due right now?
  • What's our checkout conversion rate by product?

Install

Install Polar MCP in your agent

Pick your app and Sequel installs itself: a one-click link where the client supports it, that client’s own few steps where it doesn’t. Every route signs in with your Sequel account over OAuth, so there is no API key to copy and nothing to keep in sync.

Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex, Grok, Muse, dots and any other MCP app

Already have an MCP client?

https://api.sequel.sh/mcp

Add it as a remote (streamable HTTP) server and sign in when prompted. Skills come with it; nothing else to install. Manual setup per client

Choose your app

  • Claude

    One click, opens in the app

  • Cursor

    One click, opens in the app

  • VS Code

    One click, opens in the app

  • ChatGPT

    Turn on developer mode, then add Sequel. About two minutes.

  • Claude Code

    Run one command, then sign in with /mcp.

  • Codex

    Run one command, then sign in.

  • Gemini CLI

    Run one command, then sign in with /mcp auth.

  • Grok

    Add Sequel as a connector and sign in.

  • Grok Bot

    Paste this to the bot. It registers Sequel and asks you to sign in.

  • Muse

    Muse writes its own connector. One message is the whole setup.

  • dots

    Add Sequel in ChatGPT; your dot picks it up with no extra step.

  • OpenCode

    Add Sequel as a remote server from the OpenCode CLI.

  • Other MCP app

    Any client that speaks remote MCP can connect with this URL.

Skills

Playbooks that run on Polar

Step-by-step procedures your agent follows on your Polar data, instead of improvising a query. Browse all skills

Dispute and refund risk monitor

Track chargeback and dispute activity and refund rate against the Visa VAMP and Mastercard ECM thresholds that get a payment account fined or shut off, and find which products, plans or cohorts generate them. Covers dispute rate versus dispute activity, per-network denominators and dispute-fighting economics.

Failed payment and involuntary churn audit

Separate customers who chose to leave from cards that simply declined: failed payments, declined renewals and involuntary churn, and where in the dunning and retry sequence the recovery is being lost. Covers involuntary churn share, first-attempt failure rate, payment recovery rate, decline codes and which accounts are sitting in dunning right now.

Pipeline coverage and quota gap check

Check whether open pipeline is enough to hit the quota or revenue target this quarter: pipeline coverage ratio, weighted pipeline, quota gap, and how many deals still need creating, derived from your own win rate rather than a 3x rule of thumb.

Price change and legacy pricing impact

We raised prices, so what actually happened? Measures the effect of a price increase or new pricing page on cancellations, plan mix, conversion and revenue per account, using the never-migrated legacy cohort as a control, and sizes the revenue still sitting on old grandfathered prices and what those accounts would be worth at current list price.

Subscription revenue health

Track MRR movement, churn, subscriptions that failed to renew, failed payments and refunds to separate genuine growth from collection problems.

Trial and free to paid conversion audit

Measure trial to paid and free to paid conversion properly by cohorting on trial start date, then split genuine non-conversion from trials that wanted to pay but whose first charge failed. Covers trial conversion rate, time to convert, trial length comparison and trial abuse screening.

Frequently asked questions

How do I connect Polar to Sequel?

In Polar, go to Organization Settings → Developers → New Token and create an Organization Access Token with read-only scopes (metrics:read, orders:read, subscriptions:read, customers:read, products:read, payments:read, refunds:read, disputes:read, discounts:read, checkouts:read, events:read, meters:read, customer_meters:read, organizations:read). Paste the token into Sequel's Polar connector and click Test. Leave the environment field blank for production, or enter 'sandbox' to connect a Polar sandbox organization.

Can Sequel change anything in my Polar account?

No. The connector exposes read-only tools only — it cannot create, refund, cancel, or modify any order, subscription, customer, product, or discount. Granting only the :read scopes on your token enforces that at Polar's end too.

Does Sequel recalculate my revenue metrics?

No, and that's the point. Polar computes MRR, ARR, churn, LTV and 50-odd other metrics itself, and Sequel reads those figures directly. You get the same numbers as the Polar dashboard, already net of refunds and proration, rather than an approximation reconstructed from a list of orders.

Can I ask about payouts or my Polar balance?

Not currently. Polar's public API has no payouts or balance endpoints, so those figures aren't reachable by any integration, including Sequel. Revenue questions work fine — just note that revenue is not the same as what lands in your bank account, since it's before Polar's fees and payout timing.

Does Sequel store my Polar data?

No. Query results are returned to your session and discarded; only your access token is stored, encrypted at rest with AES-256-GCM. You can revoke the token in Polar at any time.

Start analyzing your Polar data today

Connect in minutes — then ask across all your data, not just one source.