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

MealMe API vs Zillow in Claude

MealMe API scores 38.4 (E) on agent readiness against Zillow in Claude's 28.7 (F), and leads in 4 of 7 scored categories. Zillow in Claude leads on security & auth, payments & pricing and maintenance & community. Both do product search for shoppers.

Best shopping and order APIs for AI agents buying for a person · All 41 shopping comparisons

Best recipe, nutrition and meal planning APIs for AI agents · All 28 cooking comparisons

Which one, for what

MealMe API E

Best for Agents that must place a real restaurant or grocery order in the US or Canada, or compare live prices across stores, and can hold a card on the account.

Ahead on

  • Schema & documentation, 72 against 9
  • Agent ergonomics, 69 against 33

Watch for

One key with no scopes, read-only mode, expiry or rotation documented, sent in a custom Id-Token header

Zillow in Claude F

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

Ahead on

  • Security & auth, 32 against 26
  • Payments & pricing, 50 against 20
  • Maintenance & community, 35 against 6

Also in its favour

  • No key needed to call it
  • A hosted endpoint, with nothing to install

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 MealMe API +63

MealMe API 72

The reference pages are generated from an API description with operation ids (get_search_store_v3), named response schemas (Product_Search_Output) and typed parameters, but no spec file URL was found on the docs, llms.txt or the site (15 of 25). llms.txt at mealmeapi.readme.io and mealme.ai, and every page as Markdown (10). Each operation states its purpose and coverage; several descriptions are truncated in the index and none says when not to use it (12 of 20). Enums on sort, store_type, user_country and search_focus, required flags on latitude and longitude, conditional requirements written in prose (11 of 15). Request and response examples per endpoint, a Create Order errors page with 17 entries, and 400, 401 and 429 schemas on each operation (12 of 15). Versioned paths (v2 to v4) and dated release notes that call out breaking changes, the newest of 6 May 2025 (12 of 15). Total 72.

Zillow in Claude 9

Graded from Anthropic's directory entry 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 release gives two example prompts, with no tool examples or error responses (2 of 15). The URL carries /api/v2, with no changelog (3 of 15). Total 9.

Agent ergonomics MealMe API +36

MealMe API 69

Store search takes a projections list to choose response fields and a fetch_quotes switch that the docs say greatly increases response time, so responses can be sized (20 of 25). Page and next_page pagination, bounding-box, distance, rating, price, cuisine and open filters, maximum_miles defaults (18 of 20). Distinct status codes, 406 for a closed or out-of-range store, 420 for an unavailable product, 422 for checkout errors, each with a message naming the field or product (16 of 20). No idempotency key; the two-step order (202 quote, then place) and customer_order_id lookup are the safe-retry route (8 of 20). Only latitude and longitude required for search and sensible defaults, but no official SDK in any language, only an iframe embed (7 of 15). Total 69.

Zillow in Claude 33

Graded from the directory's tool list, 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.

Payments & pricing Zillow in Claude +30

MealMe API 20

No x402, MPP or L402 (0). $0.10 per successful call and $250 a month published without login (20). No free tier or trial; a card must be added before the key is created (0). Signup is a browser form with email, password and card (0). Total 20.

Zillow in Claude 50

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.

Maintenance & community Zillow in Claude +29

MealMe API 6

Read as a closed service. The newest dated change is the release note of 6 May 2025 (Get Inventory v4), more than 180 days before 3 November 2026; the pricing and dashboard pages carry no date (0 of 30). No dated change in the last 90 days (0 of 20). A support address, release notes and no community channel (6 of 15). No official SDKs (0). No package to judge (0). Total 6.

Zillow in Claude 35

Closed service. Zillow announced it on 19 October 2026, two days ago (30 of 30). One dated change in 90 days, the launch, with the directory's August 2026 added date before it (0 of 20). Zillow's help centre at www.zillow.help is the directory's support link and is readable, but it has no article on the connector in its sitemap, and there's no changelog (5 of 15). No com.zillow entry in the official MCP registry. Third-party servers hold the zillow names there (0 of 15). No package (0 of 10). Total 35.

Security & auth Zillow in Claude +6

MealMe API 26

One API key per account in a custom Id-Token header, with no scopes, expiry, rotation or revocation documented (10 of 30). place_order defaults to false and charge_user can be turned off, so an agent can quote without buying, but there is no read-only key (8 of 20). Store descriptions, menus and support-chat messages are untrusted content with no guidance (3 of 15). Get Orders and a tracking webhook give order history; no per-call log for the operator is documented (5 of 15). No security.txt (400), disclosure policy, bug bounty or certification found; the Enterprise plan names a security review (0 of 20). Total 26.

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 release says tours, agent contact and financing can follow in the same conversation, and how that is 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.

Score by category

CategoryWeight this runMealMe APIZillow in ClaudeEdge
Reliability16%201915MealMe API +4
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2729MealMe API +63
Agent ergonomics13%16.26933MealMe API +36
Security & auth14%17.52632Zillow in Claude +6
Payments & pricing10%12.52050Zillow in Claude +30
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8635Zillow in Claude +29
Transparency & trust7%8.84745MealMe API +2
Negative events≤1500
TotalE 38.4/100F 28.7/100

Facts side by side

FactMealMe APIZillow in Claude
KindHTTP APIMCP server
VendorMealMe, Inc.Zillow Group
Hosted endpointno (local only)https://mcp.zillow.com/api/v2
Transports
AuthAPI keyNone
PricingPay per useFree
x402nono
LicenceProprietary service under the MealMe API and SDK Terms of UseProprietary hosted service. No source published
Tools exposed09
Read-only variant documentednono
llms.txtyesno
Last release2025-05-062026-10-19
Terms last updated2025-04-04couldn't be read
Privacy policy last updated2025-04-042025-11-15
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 noticeyescouldn't be read
Arbitration or class-action waiveryescouldn't be read
Agent reviewsnone3/5 (4)

How the scores have moved

Verdicts

MealMe API

An agent can search stores and products, fetch live quotes and place a real order through one REST API priced at $0.10 a successful call. One all-powerful key, no rate limit figures, no status page, no idempotency key on orders and release notes that stop at 6 May 2025 are the limits.

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

MealMe API

  1. Send the key as the Id-Token header, not Authorization. Only latitude and longitude are required for store search; address fields become required when fetch_quotes is true and pickup is false
  2. Call Create Order with place_order false first, read the 202 final quote, then place it; keep your own customer_order_id and look it up before any retry, since no idempotency key exists
  3. Set projections on store search to the fields you need; fetch_quotes greatly increases response time per the docs
  4. Keep use_new_db the same across store search, Get Inventory and Get MealMe Store, or the store ids will not match
  5. Treat 406 (store closed, out of range, no delivery), 420 (product unavailable) and 422 (checkout error) as fixes to make, not transient failures

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, MealMe API or Zillow in Claude?

MealMe API scores 38.4 (E) on agent readiness against Zillow in Claude's 28.7 (F), and leads in 4 of 7 scored categories. Zillow in Claude leads on security & auth, payments & pricing and maintenance & community.

Do MealMe API and Zillow in Claude need an API key?

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

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

No hosted endpoint is listed for MealMe API. Zillow in Claude has a hosted endpoint at https://mcp.zillow.com/api/v2.

Other comparisons with MealMe API 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.