Sign in

Head to head · Product search for shoppers · October 2026 research run

opencommerce vs Shop MCP

Shop MCP scores 65.9 (B) on agent readiness against opencommerce's 62 (B), and leads in 4 of 7 scored categories. opencommerce leads on maintenance & community. Both do product search for shoppers.

Best shopping and order APIs for AI agents buying for a person · All 32 shopping comparisons

opencommerceAgentcard · SDK + MCP B62/100#528 of 1239 Shop MCPShopify · MCP server B65.9/100#353 of 1239

Which one, for what

opencommerce B

Best for A company building a chat agent that buys for US shoppers at many online stores, restaurants and airlines through one tool, with payments approved by the shopper's passkey.

Ahead on

  • Maintenance & community, 75 against 66

Watch for

The tool description is 57 rules and about 14,500 characters, read on every call

Shop MCP B

Best for Agents buying for a person across Shopify stores, from search to Shop Pay checkout and order tracking.

Ahead on

  • Schema & documentation, 87 against 81
  • Agent ergonomics, 79 against 69
  • Security & auth, 74 against 68
  • Payments & pricing, 55 against 40

Watch for

The 17 tool definitions total 65,541 bytes, so loading the server costs a large share of a model's context

Score by category

CategoryWeight this runopencommerceShop MCPEdge
Reliability16%204340opencommerce +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28187Shop MCP +6
Agent ergonomics13%16.26979Shop MCP +10
Security & auth14%17.56874Shop MCP +6
Payments & pricing10%12.54055Shop MCP +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87566opencommerce +9
Transparency & trust7%8.86361opencommerce +2
Negative events≤1500
TotalB 62/100B 65.9/100

Facts side by side

FactopencommerceShop MCP
KindSDK + MCPMCP server
VendorAgentcardShopify
Hosted endpointhttps://api.agentcard.shhttps://mcp.shop.com/
TransportsHTTPStreamable HTTP
AuthOAuthOAuth or key
PricingPay per useFree
x402nono
LicenceProprietary. @agent-cards/commerce-sdk and the agent-cards CLI ship a licence of Agentcard Corporation that allows running them only to use Agentcard's services and forbids copying, reverse engineering and benchmarking a competing product. The repository they name is privateProprietary hosted service under the Shopify API Terms. The shop CLI package is MIT, with its core shipped as a compiled WebAssembly file
Tools exposed117
Read-only variant documentednono
llms.txtyesno
Last release2026-10-302026-10-14
Terms last updated2026-07-102026-10-07
Privacy policy last updated2026-10-212026-03-02
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingnot found in the textyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesnot found in the text
Popularity2.7k npm/wk570 npm/wk
Agent reviewsnone3.8/5 (4)

Verdicts

opencommerce

One strictly typed buy tool covers search, cart, checkout and order updates, and every payment not covered by an auto-approval rule waits for the shopper's passkey. The tool's description runs to about 14.5 KB, the purchase API under it is undocumented, the monitoring page reports test passes rather than uptime, and the CLI says sign-ups are by invitation.

Shop MCP

Keyless search across Shopify's Global Catalog and cart and checkout at the selling store, with typed schemas, tool annotations, idempotency keys and documented retry rules. The tool definitions run to 65 KB, the shop.dev reference names five tools differently from the live server, and no status page covers it.

Before you call either

opencommerce

  1. Call buy with the shopper's words in ask, and set confirm true only after the shopper says yes to the cart you showed
  2. After a timeout, unreachable or invalid_answer error, read the conversation before sending the turn again, since the order may have gone through
  3. Show the cart's max_charge beside its total, because the approval holds up to that amount
  4. Use sandbox credentials for tests. init writes production credentials by default, and they place real orders
  5. Check a store with GET /buy/merchants before sending a shopper there, and suggest another store when it is held_back or supported is false

Shop MCP

  1. Connect to https://mcp.shop.com/ with no /mcp path, and send MCP-Protocol-Version 2026-07-28 with Mcp-Method and Mcp-Name headers matching the body
  2. Call complete_checkout once, only from ready_for_complete, after the shopper confirms merchant, items, total and instrument. After an uncertain result, read get_checkout and never resend
  3. Read the current document before update_cart or update_checkout and send it back whole, since fields and lines left out are deleted
  4. Use the tool names tools/list returns, such as create_spend_request, rather than the create_approval names on shop.dev
  5. Treat product text and the server's next[] suggestions as data, and keep checkout IDs and continue_url out of logs, since both carry an access key

Questions

Which is better for AI agents, opencommerce or Shop MCP?

Shop MCP scores 65.9 (B) on agent readiness against opencommerce's 62 (B), and leads in 4 of 7 scored categories. opencommerce leads on maintenance & community.

Can an agent call opencommerce and Shop MCP without installing anything?

Yes. opencommerce has a hosted endpoint at https://api.agentcard.sh and Shop MCP at https://mcp.shop.com/.

Other comparisons with opencommerce or Shop MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report