Connect Stripe MCP to your AI Agents

Ask your Stripe data anything. MRR, churn, refunds — answered in plain English.

Example prompts

Everything you can ask your agent about your Stripe data.

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

Connect to your agent
What you can ask your agent
  • What's our MRR for May, broken down by plan?
  • How many customers churned last month?
  • Show me the top 10 customers by lifetime revenue.
  • What were our Stripe fees in Q1?
  • List failed payment intents in the last 7 days with the failure reason.

Sequel CLI

Install Stripe MCP to your agent

The Sequel CLI installs Stripe into your coding agent in one step — it signs you in, provisions a scoped API key, and writes the right config to the right place. No keys to copy by hand.

Prefer npm? npm install -g @sequelsh/cli@latest works too.

  1. 1

    Install the Sequel CLI

    One line installs the latest CLI with whatever package manager you have.

    curl -fsSL https://sequel.sh/install | sh
  2. 2

    Sign in

    Authenticate in your browser and pick an organization.

    sequel login
  3. 3

    Install into your agent

    Run install and pick an agent from the list, or target one directly by its slug.

    sequel install
    • Claude Code
      sequel install claude-code
    • Claude
      sequel install claude
    • Cursor
      sequel install cursor
    • VS Code
      sequel install vscode
    • Windsurf
      sequel install windsurf
    • Zed
      sequel install zed
    • Codex
      sequel install codex
    • OpenClaw
      sequel install openclaw
    • Hermes
      sequel install hermes

Frequently asked questions

How do I connect Stripe to Sequel?

Create a Restricted Key in your Stripe Dashboard with read-only permissions on the resources you want Sequel to query (customers, charges, invoices, subscriptions, etc.), paste it into Sequel's Stripe connector, and click Test. The whole process takes under a minute.

Should I use a Secret Key or a Restricted Key?

Always prefer a Restricted Key. It lets you scope access exactly to the resources Sequel needs (read-only), and you can revoke or rotate it from the Stripe Dashboard at any time without affecting the rest of your integrations.

Does Sequel use Stripe Connect / OAuth?

No. Stripe Connect OAuth is designed for platforms that act on behalf of merchants — marketplaces, billing-on-behalf-of, etc. Sequel reads your own Stripe data, where a Restricted Key is the simpler, narrower grant.

Can Sequel make changes to my Stripe account?

No. The Stripe connector ships only read tools (list customers, list charges, get balance, search, etc.) and you should pair it with a read-only Restricted Key for defense in depth.

Can I query both test and live Stripe data?

Yes. Create two separate connections — one with a test-mode key (rk_test_…) and one with a live-mode key (rk_live_…). Sequel keeps them isolated, and the connection name makes it obvious which is which.

Does Sequel store my Stripe data?

No. Sequel queries the Stripe API at the moment you ask a question and discards the results once they're shown to you. Only your Restricted Key is stored, encrypted at rest with AES-256-GCM.

Can I combine Stripe with other data sources?

Yes. Connect Stripe alongside Postgres, BigQuery, Google Analytics, or any other Sequel source and ask cross-source questions — like 'Show me MRR from Stripe alongside signups from Postgres by week'.

How fresh is the data?

It's live. Each query hits the Stripe API directly, so what you see is what Stripe has right now. The balance ledger and account events update within seconds of the underlying transaction.

What about Stripe Sigma — do I still need it?

Sigma is great for ad-hoc SQL if you already know SQL and the Stripe schema. Sequel replaces the parts of that workflow you don't enjoy: writing the SQL, remembering the column names, and waiting for the editor — you just ask a question.

Start analyzing your Stripe data today

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