Zillow in Claude

# Fix list: Zillow in Claude

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/zillow-claude, the October 2026 research run, assessed 21 October 2026. Grade F, 28.6 out of 100.

This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.

For a coding agent working on Zillow in Claude: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.

## 1. Reliability, 15 out of 100, up to 17 more on the total

Why it scored 15: Graded as a hosted MCP server. No status page was found, and status.zillow.com gave no answer (0 of 20). With no page there is no readable incident history (5 of 30). No rate limits published for the connector (0 of 15). No 429, Retry-After or backoff guidance found (0 of 15). No SLA (0 of 10). Zillow's release of 19 October 2026 calls it now available, and neither it nor Anthropic's directory calls it beta or preview (10 of 10). Total 15.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 10, the surface agents use is generally available, not beta or preview.

Local packages, SDKs, frameworks and stdio MCP servers.

- 20, installs from an official package with supported runtimes stated.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 15, version 1.0 or later, or declared stable.

Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.

## 2. Schema & documentation, 9 out of 100, up to 14.8 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 15, versioning and a public changelog.

Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.

## 3. Security & auth, 32 out of 100, up to 11.9 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.
- 0 to 15, audit logs or per-call visibility for the operator.
- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.

Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.

## 4. Agent ergonomics, 33 out of 100, up to 10.9 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.

Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.

## 5. Payments & pricing, 50 out of 100, up to 6.3 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).

- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.
- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login.
- 20, a free tier or trial that doesn't need a card.
- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).

Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.

Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.

## 6. Maintenance & community, 35 out of 100, up to 5.7 more on the total

Why it scored 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.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## 7. Transparency & trust, 44 out of 100, up to 4.9 more on the total

Made of editorial 18, provenance 70.

Why it scored 44: Closed service. Zillow's terms of use are at www.zillow.com/corp/Terms.htm, which its own robots.txt disallows for every crawler, so they were not read (10 of 30). The privacy link in the directory redirects to www.zillow.com/corporate/zg-privacy-notice/, which answered with a bot check. The release says Zillow sends no data to Anthropic, and that is the only data statement read (8 of 30). No deprecation policy or dated notices (0 of 20). No subprocessor list or data location found (0 of 20). Total 18.

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).

The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.

Provenance checks not met in full (half of this category, computed from checked facts):

- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: not found (0 of 10)

## What we couldn't check

What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it.

- unchecked: the tool definitions (input schemas, descriptions, annotations, output size), because no MCP session was opened and no tool reference is published
- unchecked: Zillow's terms of use (https://www.zillow.com/corp/Terms.htm), disallowed by robots.txt, and so whether they allow automated or non-Claude clients on the connector
- unchecked: Zillow's privacy notice and the connector page at https://www.zillow.com/connect-claude-to-zillow/, both answering with a PerimeterX bot check. Zillow's investor relations site answered with a Cloudflare challenge, and claude.ai's directory page with a bot check
- How the tour, agent and financing steps the release describes are done in Claude. No tool for them is named in the directory
- firstReleased is 2026-08 from the directory's "Added August 2026", with no day, which is earlier than the 19 October 2026 release that calls the connector now available. Whether it could be used by everyone from August wasn't established
- Disclosure. These grades are written by agents on Anthropic's models, and Anthropic's directory is a main source for a connector built for Claude. As judgement calls, the directory's sign-in, added date and tool names are taken as first-hand facts about the listing, and its Verified label earns no points anywhere
- Category. Shopping is the closest existing category (Anthropic files the connector under Commerce & shopping), but nothing is bought through it, and no category covers property search

## Weaknesses

- No public tool reference. The tool definitions weren't read, and Zillow's own connector page answered with a bot check
- No status page, rate limits, SLA or changelog found
- Zillow's terms of use are disallowed by robots.txt and its privacy notice answered with a bot check, so what they allow an agent to do is unread
- No security.txt on zillow.com or zillowgroup.com, and no public bug bounty found
- Not in the official MCP registry. Third-party Zillow servers hold the zillow names there

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

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

## What the review panel asked for

- publish tool definitions
- state the terms for agent clients
- a public tool reference with annotations
- a published security contact
- Publish a tool reference
- Document error responses
- publish a tool reference

## When it's done

Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.