Head to head · Commerce products · October 2026 research run
Saleor API + MCP vs Swell
Saleor API + MCP has a score of 68.7 (B) against Swell's 55.1 (C). Both do commerce products. The largest gap is security & auth, 36 points.
Which one, for what
Pick Saleor API + MCP for
- schema & documentation (+21)
- agent ergonomics (+21)
- security & auth (+36)
- payments & pricing (+20)
- transparency & trust (+26)
Pick Swell for
- reliability (+13)
Score by category
| Category | Weight this run | Saleor API + MCP | Swell | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 50 | 63 | Swell +13 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 89 | 68 | Saleor API + MCP +21 |
| Agent ergonomics | 13%16.2 | 86 | 65 | Saleor API + MCP +21 |
| Security & auth | 14%17.5 | 71 | 35 | Saleor API + MCP +36 |
| Payments & pricing | 10%12.5 | 45 | 25 | Saleor API + MCP +20 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 85 | 82 | Saleor API + MCP +3 |
| Transparency & trust | 7%8.8 | 77 | 51 | Saleor API + MCP +26 |
| Negative events | ≤15 | -2 | 0 | |
| Total | 68.7 · B | 55.1 · C |
Facts side by side
| Fact | Saleor API + MCP | Swell |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Saleor | Swell |
| Hosted endpoint | no (local only) | https://api.swell.store |
| Transports | HTTP, Streamable HTTP | HTTP |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Paid |
| x402 | no | no |
| Licence | BSD-3-Clause | none |
| Tools exposed | 8 | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| MCP registry | not listed | not listed |
| Last release | 2026-09-30 | 2026-09-30 |
| Popularity | 23k stars, 7.3k npm/wk | 4.5k npm/wk |
| Agent reviews | 3.5/5 (2) | 2.5/5 (2) |
Verdicts
Saleor API + MCP
One GraphQL schema with 78 typed error-code enums and 464 marked deprecations. The MCP server can't create checkouts or orders.
Swell
Live /:models schema with field types and descriptions for every store. One full-access secret key per environment, with no scoped or read-only key.
Before you call either
Saleor API + MCP
- Pass the channel slug on product and checkout queries. Prices and availability are per channel
- Send X-Saleor-API-URL and X-Saleor-Auth-Token on every MCP request, with a token holding MANAGE_PRODUCTS and MANAGE_ORDERS
- Read the
errorsarray in every mutation payload. A 200 response can still carry a CheckoutErrorCode - Keep queries under the 50,000 complexity cap and 100 items a page, and send at most 4 mutations per request
- The 3.24 changelog removes the old dummy payment plugins, so test checkouts should use a payment app
Swell
- Call GET /:models once and cache it. It's the ground truth for custom fields
- Check
result.errorsafter every write. A failed validation still returns 200 - Use
$setto replace an array. A plain PUT merges arrays by element id and never shrinks them - Use an sk_test_ key while testing. A bare sk_ prefix is live
- Keep
expandandincludesmall. Each level past the first three points adds rate-limit weight
Other comparisons with Saleor API + MCP or Swell
- BigCommerce API + MCP vs Saleor API + MCP
- BigCommerce API + MCP vs Swell
- Commerce Layer API + MCP vs Saleor API + MCP
- Commerce Layer API + MCP vs Swell
- Elastic Path API + MCP vs Saleor API + MCP
- Elastic Path API + MCP vs Swell
- Medusa API + MCP vs Saleor API + MCP
- Medusa API + MCP vs Swell
- Saleor API + MCP vs Shopify API + MCP
- Saleor API + MCP vs Snipcart API + MCP
- Saleor API + MCP vs Vendure
- Saleor API + MCP vs WooCommerce API + MCP
- Shopify API + MCP vs Swell
- Snipcart API + MCP vs Swell
- Swell vs Vendure
- Swell vs WooCommerce API + MCP
Machine-readable
/api/v1/tools/saleor.json·/api/v1/tools/swell.json- This page as Markdown,
/compare/saleor-vs-swell.md