What is homes-mcp CLAUDE.md?

A set of instructions for working on homes-mcp, a connector that reads Homes.com real-estate pages through a signed-in Chrome tab.

Understanding the connector's tools, architecture, browser-session setup, and development commands.

It documents how the connector works and how to develop or operate it without guessing its commands or data flow.

How chrischall/homes-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/homes-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/chrischall/homes-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chrischall/homes-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/chrischall/homes-mcp/claude-md.svg)](https://agentmods.dev/instructions/chrischall/homes-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/chrischall/homes-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/homes-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 5,401 This file is loaded in full into every session.

When invoked 5,401 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.05401	$0.05401
Opus 5	$0.02701	$0.02701
Sonnet 5	$0.01080	$0.01080
Haiku 4.5	$0.00540	$0.00540

Measured 3d ago against content hash 1c73a1cad6e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

homes-mcp CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Don't add IP-rotation or TLS-impersonation libraries. The whole design is "every request rides the user's own browser session via fetchproxy." Adding cycletls / curl-impersonate / Playwright would replace that with a s

CLAUDE.md · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — homes-mcp

Guidance for Claude working in this repo.

TL;DR

homes.com MCP server. Default and only transport: localhost WebSocket via @fetchproxy/server — the companion browser extension is installed separately rather than embedded. Every HTTP call to homes.com is dispatched through the user's signed-in Chrome tab — each request rides their existing session (cookies, TLS, JS context) exactly as if they'd clicked it themselves.

This is a "Pattern A" fetchproxy MCP (every call rides through fetchproxy), not "Pattern B" (one bootstrap call then direct fetch). homes.com gates traffic through AWS WAF at the session level, so the in-session routing has to be per-call.

Tool surface

Tool	File	Endpoint	Kind
`homes_search_properties`	`tools/search.ts`	`GET /<city-slug>-<state>/` SSR — parse JSON-LD `CollectionPage.mainEntity.itemListElement[]`	read
`homes_get_property`	`tools/properties.ts`	`GET /property/<slug>/<propertyId>/` SSR — parse JSON-LD `RealEstateListing` node	read
`homes_get_property_photos`	`tools/photos.ts`	Same SSR page as `get_property` — scrape `<img>` tags filtered to the homes.com CDN	read
`homes_compare_properties`	`tools/compare.ts`	Concurrent `get_property` calls across N targets	read
`homes_calculate_mortgage`	`tools/mortgage.ts`	(local; no network)	read
`homes_calculate_affordability`	`tools/affordability.ts`	(local; no network)	read
`homes_healthcheck`	`tools/healthcheck.ts`	`/robots.txt` round-trip + bridge diagnostics via the shared `registerBridgeHealthcheckTool` (`@chrischall/mcp-utils/fetchproxy`); reports the 2.5.0 extension-link state (`bridge.session_state` / `pending_pair_code` / `extension_connected`) and `error.kind` incl. `session_not_ready` — a probe timeout while `session_state` is `pair_pending`, `extension_disconnected`, or `no_session` is re-kinded to `session_not_ready`, because the 18s probe deadline fires before fetchproxy's 30s session-ready wait and would otherwise report a pending pair code as a tab timeout; `linked` stays a timeout (the tab really is the problem) and `not_listening` stays a timeout so the `no_role` hint still wins	read
`homes_get_property_history`	`tools/history.ts`	Same SSR detail page — parse Property/Purchase/Mortgage History tables	read
`homes_get_tax_history`	`tools/history.ts`	Same SSR detail page — parse Tax History table	read
`homes_get_nearby_listings`	`tools/nearby.ts`	Same SSR detail page — scrape "Homes for Sale Near" link cards	read
`homes_get_market_report`	`tools/market.ts`	`GET /<city-slug>/sold/` — derive median/avg from JSON-LD itemListElement	read
`homes_get_saved_homes`	`tools/saved.ts`	`GET /customer/dashboard/favorites/` — auth-gated DOM scrape	read (auth)
`homes_get_saved_searches`	`tools/saved.ts`	`GET /customer/dashboard/saved-searches/` — auth-gated DOM scrape	read (auth)
`homes_estimate_rent_vs_buy`	`tools/rent-vs-buy.ts`	(local; no network — caller supplies `monthly_rent`; homes.com has no rental signal — see "Rental data gap" below)	read
`homes_get_by_address`	`tools/by-address.ts`	Structured smartsearch typeahead (`POST /routes/res/consumer/smartsearch/autocomplete/`) → slug `GET /<address-slug>/` (collection or single `RealEstateListing` detail) → city/zip search fallback. Every candidate verified via realty-core `addressMatch` (whole-token street + numeric anchor) plus a unit guard. Surfaces `matched_via: "typeahead" \| "slug" \| "search_fallback"` on hits; `{ resolved: false, error }` on miss; retryable `status: "timeout"` on a bridge timeout.	read
`homes_resolve_addresses`	`tools/resolve-addresses.ts`	Bulk `homes_get_by_address` — up to 100 `{ address, city, state, zip? }`, same rungs/verification, input order preserved, per-row outcomes (`property_hash`→`property_id`).	read
`homes_bulk_get`	`tools/bulk-get.ts`	Bulk `homes_get_property` — up to 200 URLs, per-row errors captured, input order preserved (structured records only).	read
`homes_get_history`	`tools/history.ts`	Same SSR detail page — combined price + tax history (`listing_events`, `ownership_events`, `lien_events`, `events_normalized`, `tax_records`). Preferred over the two deprecated split tools.	read
`homes_get_session_context`	`tools/sessions.ts`	(local; shared session registry) — list all registered logical sessions + `active_session_id`	read
`homes_register_session`	`tools/sessions.ts`	(local; shared session registry) — register/refresh a session keyed by `account_identity` (required); optional `auth_expires_at`; `mark_active` (default false) registers-and-activates	write (registry)
`homes_set_active_session`	`tools/sessions.ts`	(local; shared session registry) — switch the active logical session by `session_id`	write (registry)

Read the full file on GitHub · 218 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

3d ago Changed · +7 lines · +439 tokens per session 1c73a1cad6e4
4d ago Changed · +3 lines · +215 tokens per session 252d72a87ef4
7d ago First seen · 208 lines · 4,747 tokens per session scan A 7ba5172ff87a

Subscribe to this mod's changes

homes-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/homes-mcp (0 stars, last pushed today), licensed MIT. It adds 5,401 tokens to every session, about $0.0270 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

homes-mcp: Instructions file for Claude Code