What makes zillow-fpx notable?

1.5K downloads. Trust evidence available

How should zillow-fpx be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

zillow-fpx

Query zillow.com (US real-estate portal) from a shell with the fpx CLI (@fetchproxy/cli) instead of running the zillow-mcp server — search listings, pull a full property record by zpid, price/tax/Zestimate history, photos, market reports, and your signed-in saved searches/homes, all via one-shot HTTP calls through a signed-in browser tab. Use when you want Zillow data without the MCP, in a script, or on a machine where the MCP isn't installed.

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.5k

Updated

Oct 10, 2026

Version

1.2.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.5K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.5K downloadsadoption · observed Oct 10, 2026
Latest release: 1.2.2release · observed Oct 9, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17cjx1a349nz5apaqp02vgz4h85728z:zillow-fpx

Install using `clawhub skill install s17cjx1a349nz5apaqp02vgz4h85728z:zillow-fpx` in an isolated environment before connecting it to live workloads.
No published capability contract is available yet, so validate auth and request/response behavior manually.
Review the upstream CLAWHUB listing at https://clawhub.ai/chrischall/zillow-fpx before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-chrischall-zillow-fpx/snapshot"

Documentation

CLAWHUB

147,218 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: zillow-fpx
description: >-
  Query zillow.com (US real-estate portal) from a shell with the fpx CLI
  (@fetchproxy/cli) instead of running the zillow-mcp server — search
  listings, pull a full property record by zpid, price/tax/Zestimate
  history, photos, market reports, and your signed-in saved
  searches/homes, all via one-shot HTTP calls through a signed-in browser
  tab. Use when you want Zillow data without the MCP, in a script, or on
  a machine where the MCP isn't installed.
---

# Zillow via fpx (no MCP)

Zillow fronts `www.zillow.com` with a PerimeterX bot-wall that blocks
plain `curl`/Node requests, and several tools (saved searches/homes)
need an actual signed-in session. `fpx` routes every request through the
user's own signed-in browser tab (the ContextMint Bridge extension), so the
same page loads that a real visit would.

This is the same data the `zillow_*` MCP tools return — every property
tool is a scrape of Zillow's server-rendered Next.js pages
(`__NEXT_DATA__`), not a documented JSON API. No credentials are stored
anywhere; auth (for the saved-data endpoints) is just "have a signed-in
zillow.com tab open."

## One-time setup

```sh
npm install -g @fetchproxy/cli             # provides `fpx`
fpx profile add zillow --domain zillow.com # only the fetch capability is needed
fpx pair -p zillow                         # prints a pair code → approve in ContextMint Bridge
```

Requirements: the **ContextMint Bridge** browser extension installed
([releases](https://github.com/nullnet-app/contextmint-bridge/releases)), with an
open `www.zillow.com` tab, and its Chrome **Site access** allowing
`zillow.com`. (ContextMint Bridge is the renamed fetchproxy extension from the
same maintainer; build it from source or verify the release zip with
`shasum -a 256 -c contextmint-bridge-chrome-<version>.zip.sha256`.) For the saved-searches/saved-homes calls, that tab must
also be **signed in**. Pairing persists — after the first approval every
later `fpx` call reuses it.

## Core call

Every endpoint here is a GET of a server-rendered HTML page (Zillow is a
Next.js app; the whole page state is embedded as JSON in a
`<script id="__NEXT_DATA__">` tag) — there is no JSON API to hit
directly. Fetch, then pull the JSON out of the HTML:

```sh
fpx get 'https://www.zillow.com/homedetails/12345_zpid/' -p zillow > /tmp/page.html
python3 -c '
import re, sys, json
html = open("/tmp/page.html").read()
m = re.search(r"<script[^>]*id=[\"\x27]__NEXT_DATA__[\"\x27][^>]*>(.*?)</script>", html, re.S | re.I)
print(json.dumps(json.loads(m.group(1))["props"]["pageProps"]))
' | jq '.'
```

`references/pages.md` has the extractor as a reusable one-liner plus the
per-page `pageProps` field paths (search results, property detail,
photos, price/tax/Zestimate history, saved searches/homes, market
report) and the address-autocomplete GraphQL call, all transcribed from
the MCP's `src/tools/*.ts` (which parse the exact same pages).

## The one rule: resolve the loca

_meta.json

{
  "ownerId": "kn700jq4sjtf2anb0rk3ft4p7n856872",
  "slug": "zillow-fpx",
  "version": "1.2.2",
  "publishedAt": 1791588505699
}

references/pages.md

# Zillow pages for fpx

All paths below are fetched with `fpx get 'https://www.zillow.com<path>' -p zillow`.
Every page is server-rendered Next.js — the data lives in
`__NEXT_DATA__.props.pageProps`, never in a separate JSON API. Field
paths below are transcribed from the MCP's parsers
(`src/next-data.ts`, `src/tools/*.ts`) — live-verified there, not
re-captured here.

## 0. The extractor (reuse for every page below)

```sh
extract_page_props() {
  python3 -c '
import re, sys, json
html = sys.stdin.read()
m = re.search(r"<script[^>]*id=[\"\x27]__NEXT_DATA__[\"\x27][^>]*>(.*?)</script>", html, re.S | re.I)
if not m:
    sys.exit("no __NEXT_DATA__ script tag found — likely a bot-wall or redirect page")
print(json.dumps(json.loads(m.group(1))["props"]["pageProps"]))
'
}

fpx get 'https://www.zillow.com/robots.txt' -p zillow  # smoke test, no parsing needed
```

Pipe any fetched HTML through `extract_page_props` to get the page's
`pageProps` as one JSON line, then `jq` into it per the recipes below.

## 1. Search listings

Two-step dance — **always resolve before filtering**:

**Step 1 — resolve** (bare slug, no query string):

```sh
fpx get 'https://www.zillow.com/homes/Brooklyn%2C%20NY_rb/' -p zillow \
  | extract_page_props > /tmp/pp.json
jq '.searchPageState.queryState.regionSelection, .searchPageState.queryState.mapBounds' /tmp/pp.json
```

- If `searchPageState` is present with a non-empty `regionSelection` +
  `mapBounds` → you have a **region**; proceed to step 2.
- If `searchPageState` is **absent** but `pageProps.gdpClientCache` (or
  `pageProps.componentProps.gdpClientCache`) is present, Zillow resolved
  the query straight to ONE property (a homedetails page) — see §2, no
  step 2 needed.
- If `searchPageState.queryState.regionSelection` is empty AND
  `cat1.searchResults.listResults` is non-empty, Zillow returned
  address/street-level listings directly with no region to pin — use
  those listings as-is (issue #31 in the MCP).

**Step 2 — filtered search** (region pinned + your filters), only when
step 1 gave you a region:

```sh
SQS='{"usersSearchTerm":"Brooklyn, NY","filterState":{"price":{"max":900000},"beds":{"min":2}},"isListVisible":true,"isMapVisible":false,"regionSelection":[{"regionId":37607,"regionType":17}],"mapBounds":{"north":40.74,"south":40.57,"east":-73.83,"west":-74.05}}'
ENC=$(python3 -c "import urllib.parse,sys; print(urllib.parse.quote(sys.argv[1]))" "$SQS")
fpx get "https://www.zillow.com/homes/Brooklyn%2C%20NY_rb/?searchQueryState=${ENC}" -p zillow \
  | extract_page_props | jq '.searchPageState.cat1.searchResults.listResults[] | {zpid: .hdpData.homeInfo.zpid, price: .hdpData.homeInfo.price, address: .hdpData.homeInfo.streetAddress, beds: .hdpData.homeInfo.bedrooms, url: .detailUrl}'
```

`filterState` keys the MCP sets (mirror these in the JSON above):
`isForRent`/`isForSaleByAgent`/etc `{value: true|false}` (status
switches), `price {min,max}`, `beds {min}`, `baths {min}`, one
`{value:true}` flag per home type (`i

skill-card.md

## Description:

Guides agents in retrieving US Zillow listings, property details, market reports, and signed-in saved data through a browser-backed shell CLI.

This skill is ready for commercial/non-commercial use.

## Publisher:

[chrischall](https://clawhub.ai/user/chrischall)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agents use this skill to search US property listings and inspect Zillow property, pricing, tax, photo, and market data without running the Zillow MCP server. Signed-in users can also retrieve their saved searches and homes.

### Deployment Geography for Use:

United States

## Known Risks and Mitigations:

Risk: The CLI and browser extension can access Zillow pages through the user's browser session.

Mitigation: Install and pair them only if you are comfortable granting that access; review the extension before use.

Risk: Saved searches, saved homes, and exact-address queries can expose account or location data to local scripts and command output.

Mitigation: Run those examples only when needed, and avoid sharing captured outputs or temporary files containing sensitive data.

## Reference(s):

- [Zillow pages for fpx](references/pages.md)
- [ClawHub skill release](https://clawhub.ai/chrischall/skills/zillow-fpx)
- [ContextMint Bridge releases](https://github.com/nullnet-app/contextmint-bridge/releases)

## Skill Output:

**Output Type(s):** [Shell commands, Code, Guidance]

**Output Format:** [Markdown with shell and JSON examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Retrieved results may contain property addresses or signed-in saved-listing data.]

## Skill Version(s):

1.2.2 (source: server-resolved release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 17h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.