Back to cookbook

AI Prompt to Analyze Sales Transactions via PayPal's MCP Server

0 views Published

Make this prompt yours

Share

This prompt is for small business owners and sales teams who want an AI assistant like ChatGPT or Claude to pull real transaction data from PayPal through its MCP server and turn it into a plain-language sales summary, instead of exporting a CSV and building a report by hand. The model queries actual payment records and reports on totals, trends, and standout transactions.

It's built for recurring questions like how revenue compares to last month, which products or customers are driving the most volume, or whether refund rates are creeping up. Because the assistant reads live transaction data through the MCP connection, the numbers it reports reflect what actually happened in the account rather than a rough recollection.

If you plan to turn these summaries into recurring reports or outreach copy, running the prompt through Prompt Optimizer in Business mode can tighten the instructions so the output stays consistent each time you run it.

Prompt template

Make this prompt yours

prompt-template
247 tokens
ROLE: You are a sales analyst with access to PayPal transaction data through an MCP connection. CONTEXT: - Account or business name: [ACCOUNT_NAME] - Date range: [START_DATE] to [END_DATE] - Currency: [CURRENCY_CODE] - Comparison period (if applicable): [PRIOR_PERIOD] TASK: 1. Retrieve completed transactions, refunds, and chargebacks for the specified date range through the MCP connection. 2. Calculate total gross revenue, total refunds, and net revenue for the period. 3. Compare net revenue against the comparison period if one is given, and state the percentage change. 4. Identify the 3 largest individual transactions in the period. 5. Summarize the findings in plain language suitable for a non-technical stakeholder. CONSTRAINTS: - Only report figures retrieved from actual transaction data, not estimates. - Clearly separate gross revenue, refunds, and net revenue in the output. OUTPUT FORMAT: - Gross revenue: [amount] - Refunds/chargebacks: [amount] - Net revenue: [amount] - Change vs. comparison period: [percentage or "not provided"] - Top transactions: [list of 3] - Summary: [plain-language explanation]

Want it sharper? Optimize this prompt with Prompt Optimizer, check it with the Prompt Debugger or shorten it with the Token Optimizer.

Example input

example-input
44 tokens
Account: Riverside Goods Date range: Oct 1-31, 2026 Currency: USD Comparison period: Sep 1-30, 2026 How did October sales perform compared to September?

When to use it

  • You need a weekly or monthly revenue summary pulled from real PayPal transaction data instead of manually exporting reports
  • A stakeholder asks how sales compare to a prior period and you want an answer sourced from actual payment records
  • You are preparing a sales update for a meeting and need the numbers verified against real transactions, not a rough estimate
  • You want to spot your highest-value transactions in a period without scrolling through a transaction list manually

Best practices

  • State the exact date range you want analyzed instead of saying "recent" or "this month", since PayPal's reporting periods can be ambiguous
  • Ask the assistant to separate completed payments from refunds and chargebacks so the net revenue figure isn't inflated
  • Specify the currency if your account processes more than one, so totals aren't silently mixed across currencies
  • Request the raw transaction count alongside the summary, so you can sanity-check the numbers yourself

Common mistakes

  • Letting the assistant report gross transaction volume as revenue without subtracting refunds and fees
  • Not specifying a timezone, which can shift which transactions fall inside or outside the requested date range
  • Asking for trend analysis over a period too short to show a meaningful pattern, like comparing two single days
  • Treating a summary of one payment method as the full picture when sales also come through other channels

FAQs

How can I get ChatGPT or Claude to analyze my real PayPal sales instead of guessing?

With an MCP connection to PayPal, the assistant queries your actual transaction history and reports figures pulled directly from that data, rather than estimating from a description you type in.

Does this prompt work with Gemini too?

Yes, the template is plain text without vendor-specific syntax, so it works the same way across ChatGPT, Claude, and Gemini as long as the assistant has an active MCP connection to PayPal.

Why does my revenue total look higher than what actually landed in my account?

This usually means refunds, chargebacks, or PayPal fees weren't subtracted from the gross figure. Asking the assistant to report gross, refunds, and net revenue separately avoids this.

What's a good way to turn this into a prompt I reuse every month?

Run it through Prompt Optimizer in Business mode to tighten the instructions, or check its clarity first with Intelligence Score before making it a recurring report.

Found this prompt useful? Share it.

Share

More in Marketing & Sales

Marketing & Sales

ChatGPT Prompt to Write a Sales Follow-Up Email After a Discovery Call

This prompt helps sales reps and founders write a sales follow up email after a discovery call, turning call notes into a clear, personalize…

Role: You are a sales professional writing a follow-up email after a discovery call.

Context:
- Prospect name and company: [PROSPECT_NAME_AND_COMPANY]
- Key pain points or goals they mentioned: [PAIN_POINTS_OR_GOALS]
- What was discussed or demoed on the call: [CALL_SUMMARY]
- Agreed next step: [NEXT_STEP]
- Your name and role: [YOUR_NAME_AND_ROLE]

Task:
Write a follow-up email that:
1. Thanks them for their time and references one specific detail from the call
2. Briefly connects their stated pain point or goal to what you discussed
3. Confirms the agreed next step with a specific action and, if relevant, a suggested date or deadline
4. Closes with a clear, low-friction call to action

Constraints:
- Keep the email under 150 words
- Do not introduce any pricing, timeline, or commitment that wasn't part of the provided call summary
- Avoid generic opening lines like "I hope this email finds you well"

Output format:
A complete email with a subject line, written in a professional but conversational tone.

Make this prompt yours

Marketing & Sales

ChatGPT Prompt to Create a Detailed Buyer Persona for Marketing Campaigns

This ChatGPT prompt for creating a buyer persona turns scattered notes about a company's customers, such as demographics, pain points, and b…

ROLE
You are a market research analyst who builds buyer personas from customer data for marketing teams.

CONTEXT
Product or service: [PRODUCT/SERVICE NAME AND ONE-LINE DESCRIPTION]
Target market: [INDUSTRY OR MARKET SEGMENT]
Available customer information: [PASTE NOTES, SURVEY RESULTS, INTERVIEW QUOTES, CRM DATA, ETC.]

TASK
1. Identify the 1-3 distinct buyer personas suggested by the information provided, if more than one exists.
2. For each persona, define: name/title, demographics, role and responsibilities, primary goals, key pain points, objections to buying, preferred information channels, and typical buying triggers.
3. Clearly mark which details are based on provided evidence and which are reasonable inferences.
4. Note any gaps in the available information that would need more research to fill confidently.

CONSTRAINTS
- Do not fabricate specific statistics, survey numbers, or quotes that were not provided.
- Keep each persona to roughly one page of content.
- Use plain, specific language rather than generic marketing buzzwords.

OUTPUT FORMAT
For each persona, use this structure:
- Persona name and one-line summary
- Demographics and role
- Goals (3-5 bullets)
- Pain points (3-5 bullets)
- Objections to buying (2-3 bullets)
- Preferred channels and content types
- Evidence vs. inference notes

Make this prompt yours

Marketing & Sales

ChatGPT Prompt to Write a Press Release for a Product Launch or Company Announcement

This press release writing prompt is built for marketing teams and founders who need to announce a product launch, funding round, partnershi…

You are a PR professional writing a press release for [COMPANY NAME].

CONTEXT:
Announcement type: [PRODUCT LAUNCH / FUNDING ROUND / PARTNERSHIP / MILESTONE]
Key facts: [LIST THE CORE FACTS - WHAT, WHEN, WHY IT MATTERS]
Quote source: [NAME, TITLE] saying something like: [ROUGH QUOTE IDEA]
Target audience: [WHO THIS NEEDS TO REACH, e.g. tech journalists, local press, investors]
Company boilerplate: [1-2 SENTENCES ABOUT THE COMPANY]

TASK:
1. Write a headline under 15 words that states the news factually, with no marketing superlatives.
2. Write a dateline and a lead paragraph that answers who, what, when, where, and why it matters, in that order.
3. Write 2-3 body paragraphs with supporting details, each paragraph covering one supporting fact.
4. Write one attributed quote from the named source that sounds natural, not robotic.
5. End with the boilerplate paragraph and a line for media contact information.

CONSTRAINTS:
- Do not use unverifiable superlatives ("best," "revolutionary," "industry-leading") unless a specific number backs them up.
- Keep total length under 500 words.
- Flag any claim in the key facts that sounds exaggerated so it can be fact-checked before publishing.

OUTPUT FORMAT:
Return the release in standard press release format: HEADLINE, dateline, lead paragraph, body paragraphs, quote, boilerplate, contact line.

Make this prompt yours