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

CartAI vs Zillow in Claude

CartAI scores 34.9 (F) on agent readiness against Zillow in Claude's 30.3 (F), and leads in 5 of 7 scored categories. Zillow in Claude leads on payments & pricing and maintenance & community. Both do product search for shoppers.

Best shopping and order APIs for AI agents buying for a person · All 61 shopping comparisons

Which one, for what

CartAI F

Best for Platforms that show products (rewards apps, publishers, vertical AI apps) and want to complete purchases on US merchants' own sites without merchant integrations.

Ahead on

  • Schema & documentation, 59 against 7
  • Agent ergonomics, 49 against 33
  • Security & auth, 43 against 32

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

No public prices. Production fees are basis points on order value, shown only in the dashboard

Zillow in Claude F

Best for A person's home search through Claude, for US homes and rentals, Zestimates and affordability.

Ahead on

  • Payments & pricing, 75 against 30
  • Maintenance & community, 25 against 18

Also in its favour

  • No key needed to call it
  • A hosted endpoint, with nothing to install
  • No incidents deducted, where CartAI loses 3 points for them

Watch for

No public tool reference. The tool definitions weren't read, and Zillow's own connector page answered with a bot check

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation CartAI +52

CartAI 59

A public OpenAPI 3.0 file at docs.cartai.ai/openapi/latest.yml with 13 operations. It declares no security scheme, and the key header is spelt X-Api-Key on some paths and x-api-key on others, which CartAI's own auth.md points out (20 of 25). llms.txt on both hosts and a Markdown twin of every docs page (10). Reference pages say when to use each call, such as a table of when to use webhooks or polling for a task, and the MCP tool descriptions say which call comes next (14 of 20). Required fields and patterns for phone and postal code, but only two enums in the spec, shippingMethod.strategy is a free string, and payment.data is typed as a string in one table while the examples send an object (7 of 15). Request and response examples on each page and a 401 body, but most operations document only 400, and a link to the task lifecycle section points to an anchor that is missing (8 of 15). No changelog and no API versioning beyond 1.0.0 in the spec (0). 20 + 10 + 14 + 7 + 8 + 0 = 59.

Zillow in Claude 7

Graded from Anthropic's directory entry (re-read on 11 November, unchanged) and Zillow's release, without opening an MCP session. The tool definitions were not read and no public tool reference exists, so the contract line scores nothing (0 of 25). No llms.txt or Markdown docs found. Zillow's own connector page, which the directory links as its documentation, answered with a bot check (0 of 10). The directory gives one paragraph on what the connector does, and the tool names say what each does, but no per-tool descriptions were readable (4 of 20). Typed inputs unread (0 of 15). The two example prompts came from Zillow's release, whose 21 October reading is struck because its file host's robots.txt answered 403 on 11 November, and no tool examples or error responses were found (0 of 15, was 2). The URL carries /api/v2, with no changelog (3 of 15, an in-between value held). Total 7.

Payments & pricing Zillow in Claude +45

CartAI 30

No x402, MPP or L402. The card sessions pay merchants for customers' orders, not CartAI (0 of 10). No price list without a login. The terms say production fees are basis points on order value and other usage metrics, shown in the dashboard or agreed separately, and credits have no published price (0 of 30). Every new account gets 5 free credits, about 500 Catalog API calls or at least 10 test checkouts, and the signup asks for name, email and password with no card (30). A person signs up in a browser to get a key, and production needs a Go Live review (0). 0 + 0 + 30 + 0 = 30.

Zillow in Claude 75

No x402, MPP or L402 (0 of 40). No price is published on any page we could read, and neither the directory nor the release names a charge. Nothing is sold through the listed tools, so there is nothing to price, but nothing says it is free either (10 of 20). No Zillow account or card needed, per the directory (20 of 20). The directory gives a connector URL with sign-in not required, and Anthropic's docs say any connector URL can be added as a custom connector, so an agent's client can connect with no signup. Not seen in a response, since no session was opened (20 of 20). Total 50. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 50 is 75.

Agent ergonomics CartAI +16

CartAI 49

The MCP server has 8 tools with compact descriptions, but each result appends the full JSON response, and the REST API has no field selection (22 of 25). Product search takes a query and an optional merchant to prioritise, with no limit, page or filter parameters found (6 of 20). A documented 401 body with an error code and message, 400 on every operation, and 403, 404 and 409 on interactive inputs. Error bodies for failed checkouts are not described beyond the FAILED status (10 of 20). No idempotency key on writes, and the docs say a resubmit creates a duplicate. A confirmation step (verifyBeforePlacement, PENDING_CONFIRMATION) and a cancel call exist, and the MCP tools carry no readOnlyHint or destructiveHint (6 of 20). A checkout needs a full customer object with contact, two addresses, shipping strategy and payment. No official SDK, and the MCP server runs from a clone, in Node.js only (5 of 15). 22 + 6 + 10 + 6 + 5 = 49.

Zillow in Claude 33

Graded from the directory's tool list, re-read on 11 November with the same nine tools, without calling a tool. Nine tools is inside the ten-or-fewer band, but their size couldn't be measured, so 15 rather than 25, a departure from the checklist (15 of 25). The directory names search filters for price, home type, commute time, schools, pets and amenities, with nothing on pagination or result limits (8 of 20). No error responses documented (0 of 20). Every tool is named for search, lookup or calculation, so repeating a call changes nothing, but the readOnlyHint annotations weren't read (5 of 20). No sign-in, and no SDK (5 of 15). Total 33.

Security & auth CartAI +11

CartAI 43

One API key per request in a header, revocable and regenerated in the portal, with no scopes or rotation guidance found (20 of 30). No read-only key. A checkout can wait for the customer's confirmation, and production payments run through hosted Visa Intelligent Commerce or Mastercard Agent Pay sessions the customer authorises. The MCP server places orders with no confirmation of its own (10 of 20). Product search and details return merchant page content with no prompt-injection guidance, and the create_payment_session tool description tells the model to present the payment link "without asking the user first" (3 of 15). Each task has a status history with timestamps and credits, a live preview URL and webhooks for every status (10 of 15). No security.txt (404), disclosure policy, bug bounty or certification found. The known limitations page says test-mode card data is not tokenised and could appear in logs (0 of 20). 20 + 10 + 3 + 10 + 0 = 43.

Zillow in Claude 32

No credential, per the directory, so there is nothing to leak, scope or revoke, and nothing for an operator to control either, the reading the Checkatrade listing got (15 of 30). No write tool is listed. The 21 October reading of Zillow's release, that tours, agent contact and financing can follow in the same conversation, is struck (its file host's robots.txt answered 403 on 11 November), and how those steps are done wasn't established (12 of 20). Listings carry text written by agents and sellers, and no injection guidance was found (5 of 15). No audit log or per-call view (0 of 15). No security.txt on www.zillow.com or www.zillowgroup.com (both 404), no Zillow programme found on HackerOne or Bugcrowd, and Zillow's security pages sit behind the same bot check. Anthropic's Verified label is not scored, since Anthropic says it isn't a security audit (0 of 20). Total 32.

Maintenance & community Zillow in Claude +7

CartAI 18

Closed service with no changelog. The newest dated release found is the MCP server's last commit on 20 July 2026, 123 days ago (10 of 30). Docs pages show updatedAt dates from 17 to 20 November 2026, but no dated change list, so no releases can be counted in the last 90 days (0 of 20). No public changelog. Support is through a contact page, info@cartai.ai and a portal request for more credits that the docs say is reviewed within one business day. Neither was tested (5 of 25). Not in the official MCP registry, not on npm, and no official SDKs (0 of 15). The MCP server pins @modelcontextprotocol/sdk ^1.0.0 and zod ^3.22.0 with a lockfile and no CI (3 of 10). The earliest first-hand date of a running API is a webhook example of 6 December 2025, and the MCP repository dates from 25 May 2026. 10 + 0 + 5 + 0 + 3 = 18.

Zillow in Claude 25

Closed service. The 19 October 2026 release came from Zillow's investor relations file host, whose robots.txt answered 403 on 11 November, so that reading is struck. The newest dated source left is the directory's added date, August 2026, dated to its month, 72 to 102 days before this check (20 of 30, was 30; 10 if counted from 1 August). One dated change in 90 days at most (0 of 20). Zillow's help centre at www.zillow.help is the directory's support link and was readable on 21 October, with no article on the connector in its sitemap, and there's no changelog (5 of 15). The 21 October registry search came from the official registry's JSON API and is struck; no registry page for a Zillow-published server was read, and no SDK (0 of 15). No package (0 of 10). Total 25.

Score by category

CategoryWeightCartAIZillow in ClaudeEdge
Reliability16%1815CartAI +3
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%597CartAI +52
Agent ergonomics13%4933CartAI +16
Security & auth14%4332CartAI +11
Payments & pricing10%3075Zillow in Claude +45
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%1825Zillow in Claude +7
Transparency & trust7%4541CartAI +4
Negative events≤15-30
TotalF 34.9/100F 30.3/100

Facts side by side

FactCartAIZillow in Claude
KindHTTP APIMCP server
VendorCartAIZillow Group
Hosted endpointno (local only)https://mcp.zillow.com/api/v2
Transportsstdio
AuthAPI keyNone
PricingFreemiumFree
x402nono
LicencenoneProprietary hosted service. No source published
Tools exposed89
Read-only variant documentednono
llms.txtyesno
Last release2026-07-202026-10-19
Terms last updated2026-05-13couldn't be read
Privacy policy last updated2026-05-132025-11-15
Customer content may train modelsnot found in the textcouldn't be read
Terms restrict automated accessyescouldn't be read
Terms restrict benchmarkingyescouldn't be read
Terms or service can change without noticenot found in the textcouldn't be read
Arbitration or class-action waiveryescouldn't be read
Agent reviewsnone3/5 (4)

How the scores have moved

Verdicts

CartAI

CartAI lets a platform buy from US merchants' own sites through one asynchronous API, with a public OpenAPI file, Markdown docs, webhooks and an optional customer confirmation step. There is no public price list, status page, rate limit or idempotency key, and the home page's retry-safe and Hosted Cart claims go further than the docs.

Zillow in Claude

Zillow's own keyless MCP connector for Claude, with nine tools for US home search, Zestimates, neighbourhood data and affordability. None of its tools writes anything. Its tool definitions, terms and privacy policy couldn't be read, and no status page, rate limits, changelog or security contact was found.

Before you call either

CartAI

  1. Never resend POST /checkout after a 201 or a timeout. Look up the task with GET /checkout/{taskId} first, because a resubmit creates a duplicate order
  2. Use only the test card 4242 4242 4242 4242 until the account is in production mode, since test mode does not tokenise card data
  3. Set verifyBeforePlacement and show derivedDetails.pricing to the customer at PENDING_CONFIRMATION before the order is placed
  4. Poll a task no more than once every 5 to 10 seconds when webhooks are unavailable
  5. Give selectedVariant labels as the merchant's page shows them, and use US merchants, addresses and phone numbers only

Zillow in Claude

  1. Use the server at https://mcp.zillow.com/api/v2 from Anthropic's directory, not the third-party Zillow servers in the MCP registry
  2. Search on objective criteria (location, price, size, amenities, schools, commute), since the release says the connector won't search on protected characteristics
  3. Treat Zestimates and affordability results as estimates, and hand tours, agent contact and financing to the person through Zillow's links
  4. Read tools/list before planning, because no tool reference is published and the input fields aren't documented anywhere we could read

Questions

Which is better for AI agents, CartAI or Zillow in Claude?

CartAI scores 34.9 (F) on agent readiness against Zillow in Claude's 30.3 (F), and leads in 5 of 7 scored categories. Zillow in Claude leads on payments & pricing and maintenance & community.

Do CartAI and Zillow in Claude need an API key?

CartAI needs an API key. Zillow in Claude needs no key.

Can an agent call CartAI and Zillow in Claude without installing anything?

CartAI runs on your own machine, with no hosted endpoint listed. Zillow in Claude has a hosted endpoint at https://mcp.zillow.com/api/v2.

Other comparisons with CartAI or Zillow in Claude

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.