ShopTrueProfit Fee & Profit MCP: Etsy, eBay and Amazon FBA/FBM

Give your AI agent exact marketplace fee math. Etsy, eBay.com and Amazon.com (FBA and FBM) seller fees, profit, margin, break-even price and "what price do I need for a 30% margin", in one MCP server.

It runs the ShopTrueProfit fee engine. Every answer comes with an itemized fee breakdown, the assumptions used, the fee-table version and the date it was checked, and links to the official Etsy, eBay and Amazon fee pages so a person can double-check it.

• 13 tools: fees, profit and target price for each marketplace, a 3-way comparison, and free category and region lookups
• Current 2026 tables: Amazon's 2026 FBA cards (standard, apparel, dangerous goods) with peak-season rates (Oct 15 to Jan 14), the 3.5% fuel & logistics surcharge, monthly storage, the 37 referral categories with minimums and closing fees; eBay's 11 final value fee categories with per-item tiers, the $0.30/$0.40 per-order fee, Promoted Listings, the international fee and performance surcharges; Etsy's listing, transaction, payment processing for 12 regions, and Offsite Ads with the $100 cap
• Built for agents: tight JSON schemas with enums, a one-line summary on every result, and clear errors. Bad input is rejected with a message naming the field. It is never quietly "fixed".
• Deterministic and private: pure math. No scraping, no logins, no marketplace API keys, and nothing you send is stored.

Not affiliated with Etsy, eBay or Amazon. Results are estimates from published fee schedules; your marketplace statement is the final word.

Tools

Tool	What it answers	Billing
etsy_fees	What does Etsy take from this order?	1 event
ebay_fees	What does eBay take from this order?	1 event
amazon_fees	Amazon referral + FBA (or FBM) fees for one unit	1 event
etsy_profit	Profit, margin and break-even price on Etsy, given costs and ads	1 event
ebay_profit	Same for eBay	1 event
amazon_profit	Same for Amazon, FBA or FBM	1 event
etsy_target_price	Lowest price that breaks even and that reaches X% margin on Etsy	1 event
ebay_target_price	Same for eBay (handles the $10 per-order step and whole-amount bands)	1 event
amazon_target_price	Same for Amazon (handles FBA price bands and referral bands)	1 event
compare_marketplaces	The same product on Etsy, eBay and Amazon, ranked by profit	1 event
list_ebay_categories	eBay category ids and fee rules	free
list_amazon_categories	Amazon category ids, referral rates, minimums, size tiers	free
list_etsy_regions	Etsy Payments regions, currencies, processing rates	free

Every argument is described in each tool's input schema, which your MCP client shows (tools/list). Money amounts are in dollars with at most 2 decimal places (24.99 means $24.99), and percent arguments are percents (8.25 means 8.25%).

Example

Ask your agent: "I sell a $25 item on eBay with $5 shipping. It costs me $8 and the label is $4. I promote at 5%. What do I make, and what should I charge for a 30% margin?"

The agent calls ebay_profit:

{ "price": 25, "shipping_charged": 5, "item_cost": 8, "shipping_label_cost": 4, "promoted_listings_pct": 5 }

and gets back (shortened):

{
  "summary": "eBay profit $12.02 on $30.00 revenue (40.07% margin) after $5.98 fees and $12.00 costs. Break-even price $10.24 per unit.",
  "fees": { "total": 5.98, "percent_of_revenue": 19.93, "lines": [
    { "code": "final_value_fee", "amount": 4.08, "basis": "Most categories: 13.6% on the portion up to $7,500; ..." },
    { "code": "per_order_fee", "amount": 0.40, "basis": "order total $30.00 > $10" },
    { "code": "promoted_listings", "amount": 1.50, "basis": "5% of $30.00" } ] },
  "profit": { "profit": 12.02, "margin_pct": 40.07, "break_even_price": 10.24 },
  "assumptions": ["eBay.com (US) seller WITHOUT a Basic/Premium/Anchor/Enterprise Store ...", "..."],
  "fee_table": { "id": "ebay-us-2026-10-16", "verified_on": "2026-10-16" },
  "sources": [{ "title": "eBay: Selling fees", "url": "https://www.ebay.com/help/selling/fees-credits-invoices/selling-fees?id=4822" }]
}

Connect

Hosted on Apify (MCP over streamable HTTP)

Endpoint: https://<standby-url-from-the-Endpoints-tab>/mcp, with header Authorization: Bearer <your Apify API token>.

{
  "mcpServers": {
    "shoptrueprofit-fees": {
      "type": "streamable-http",
      "url": "https://<standby-url>/mcp",
      "headers": { "Authorization": "Bearer ${APIFY_TOKEN}" }
    }
  }
}

Batch runs on Apify

Start the Actor normally with input { "tool": "...", "arguments": { ... } }, or many at once with { "calls": [ { "tool": "...", "arguments": { ... } } ] } (up to 1,000). Each result is one dataset item with ok, result or error. Rejected items are listed with the reason and are not charged.

Pricing

Pay per event: one fee-calculation event per successful calculation (one MCP tool call, or one batch item). The list_* lookups and rejected inputs are free. On Apify's Standby (MCP) endpoint, Apify also bills its small platform usage for the time the server runs; see Apify's Standby billing.

What's included, what isn't

Included and kept current: everything in the fee tables listed above. Each result's assumptions lists exactly what was applied.

Not modelled (each result says so): eBay Store subscription rates; Etsy Ads cost-per-click, Etsy Plus, currency conversion and the Regulatory Operating Fee; Amazon low-inventory, inbound placement, returns processing, aged-inventory and storage-utilization surcharges, lithium battery fees, removal/disposal, the Overmax handling fee, and FBA rates after Jan 14, 2027 (not yet published; 2026 non-peak rates are used, with a warning). Ad spend you pay per click can be passed in as ad_spend.

Accuracy

• The fee engine is a verbatim copy of the ShopTrueProfit web app's fee engine, never edited by hand, and every build verifies it by SHA-256. The test suite compares this server's output field by field with the app's own functions on 1,700+ cases, including Amazon's and eBay's own published worked examples.
• Fee tables were verified against the official pages on the date in fee_table.verified_on (Etsy 2026-10-13, eBay and Amazon 2026-10-16).

Privacy

• Your tool arguments are processed in memory to compute the answer and are not stored by the server. Apify runs the infrastructure and handles your account, billing and platform logs under Apify's privacy policy. Batch runs write results to your own Apify dataset, which you control and can delete.
• No personal data is needed. Inputs are prices, costs, dimensions and categories.
• Contact and privacy questions: open an issue on this Actor's Issues tab.

License

MIT license.