Stripe in ChatGPT

Stripe is connected once in Adrails, under Integrations, with a restricted key Stripe creates with the read permissions already selected, pasted once in Adrails. Adrails reads customers, charges and refunds, subscriptions and prices, through a restricted key that has read permissions only, and ChatGPT reaches the same data through the MCP server, with your sign-in and inside the one workspace you chose.

In ChatGPT, the Stripe reads come from 4 tools: saas_performance, store_customers, business_review and integrations_status. The table above says what each one returns and gives a question to type as it is. Every result comes back twice, as exact data for the model and as a readable table for you, so a figure ChatGPT states can be traced to the call that produced it.

ChatGPT adds remote MCP servers through Developer mode, which depends on your ChatGPT plan and your workspace's policy. The server is added once, then enabled in the conversations where you want it, and ChatGPT's app settings let you switch individual tools off and refresh the list from the server.

Every client uses the same server URL, https://adrails.ai/api/mcp, and the same sign-in: ChatGPT registers itself, you sign in to Adrails, then choose the workspace and the permissions on the consent screen. Stripe needs nothing on the ChatGPT side, since it is already connected in that workspace under Integrations.

• 1. In ChatGPT Settings, turn on Developer mode
• 2. Open Plugins and add a custom MCP server named Adrails, with https://adrails.ai/api/mcp as its URL and OAuth as its authentication
• 3. Sign in to Adrails, choose the workspace and the permissions, and choose Allow access
• 4. Review the tools ChatGPT discovered, then add Adrails to a new conversation

Ask in your own words: ChatGPT picks the tool, Adrails returns the figures, and ChatGPT's model does the reasoning, so a tool call uses no agent credit. Each result carries the exact data in structuredContent.result and the same figures as readable tables.

A result is at most 256,000 bytes, so a long history is asked for in shorter ranges or pages. saas_performance, store_customers, business_review and integrations_status are the tools ChatGPT reaches for; the table above shows what each returns.

• How many active subscriptions and trials do we have, and what is MRR this month?
• Which countries did last week's new customers come from, and what do they pay?
• Check my payback estimate against the MRR and ad spend figures in this conversation.

No tool writes to Stripe. The restricted key is read-only: Adrails never charges, refunds or changes anything in Stripe. The write permissions the consent screen can offer concern ad accounts, integrations, automations, Knowledge and campaign drafts, and none of them reaches Stripe.

Each source and currency stays separate in every result: a Stripe figure is never added to a Shopify or Meta Ads one, never converted, and always named with its source, so ChatGPT can set them side by side but cannot blur them into one total.

A read covers the whole workspace, every ad account and integration it has, and never another workspace. Full customer email addresses are not stored, so ChatGPT sees a name, an email domain and a country.

Read workspace data, the one permission every connection needs, covers every integration of the workspace, Stripe included. No write permission exists for Stripe, so a member and an owner read the same data, and ChatGPT lists no tool that could change it.

Payments are read every 15 minutes, subscriptions every 30 minutes and customers every hour. Adrails' own billing also runs on Stripe, but it is separate from this connection.

Calls on one connection run one at a time, at most 60 a minute per access token, and a connection works in the one workspace you chose at consent: to work in another, connect ChatGPT again and choose it. Revoke ChatGPT under Your connections on the MCP page in Adrails; removing the server in ChatGPT does not revoke it there.