redfin-mcp: Instructions file for Claude Code

CLAUDE.md

redfin-mcp CLAUDE.md is an instructions file for Claude Code from chrischall/redfin-mcp. It costs 4,465 tokens per session, scanned A, original, MIT.

Repository instructions for a Redfin MCP server, a connector that lets coding agents search Redfin property data through the user's signed-in Chrome session. MCP is a standard way for an agent to call external tools.

In plain words
What is it for?
They are for working on property search and address lookup tools, understanding their endpoints, and building or maintaining the local WebSocket-based server.
Why use it?
They explain how requests are routed, which avoids breaking Redfin's session checks or misunderstanding the server's browser-based architecture.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md.

This is chrischall/redfin-mcp's own configuration. It tells Claude Code how to work on redfin-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything redfin-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/redfin-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/redfin-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/chrischall/redfin-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.

agentmods badge for redfin-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/chrischall/redfin-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/redfin-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/chrischall/redfin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/redfin-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for redfin-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/chrischall/redfin-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/redfin-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,465 This file is loaded in full into every session.
When invoked 4,465 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.04465 $0.04465
Opus 5 $0.02233 $0.02233
Sonnet 5 $0.00893 $0.00893
Haiku 4.5 $0.00447 $0.00447

Measured 3d ago against content hash d10eb656ae80, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

redfin-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 · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — redfin-mcp

Guidance for Claude working in this repo.

TL;DR

Redfin 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 redfin.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). Redfin validates each request at the session level, so the in-session routing has to be per-call.

Tool surface

Tool File Endpoint(s) Kind
redfin_search_properties tools/search.ts (a) GET /stingray/do/location-autocomplete?location=… → region OR address(b) GET /stingray/api/gis?region_id=…&region_type=…&… (region path) — address path short-circuits to a 1-result reply read
redfin_get_by_address tools/get-by-address.ts GET /stingray/do/location-autocomplete?location=… → first Addresses row → parse /home/<id> read
redfin_get_property tools/properties.ts (a) GET /stingray/api/home/details/initialInfo?path=… → propertyId+listingId(b) GET /stingray/api/home/details/aboveTheFold?propertyId=…&listingId=… read
redfin_get_property_photos tools/photos.ts (a) optional initialInfo to resolve IDs(b) GET /stingray/api/home/details/aboveTheFold?… (mediaBrowserInfo.photos[]) read
redfin_get_market_report tools/market.ts GET /stingray/api/region/<region_type>/<region_id>/<property_type>/market-trends read
redfin_get_price_history tools/history.ts GET /stingray/api/home/details/belowTheFold?propertyId=…&listingId=… read
redfin_compare_properties tools/compare.ts GET /stingray/api/home/details/aboveTheFold?… ×N (concurrent) read
redfin_bulk_get tools/bulk-get.ts per-target ATF/BTF (+optional /home/<id> redirect resolve) ×N (≤200, concurrent, per-row errors, hard deadline) read
redfin_resolve_addresses tools/resolve-addresses.ts GET /stingray/do/location-autocomplete?location=… ×N (≤100, concurrent) → URL/home_id per row read
redfin_get_climate_risk tools/climate.ts GET /<homedetails-path> HTML — extract floodData/fireData/heatData blocks read
redfin_get_climate_risk_bulk tools/climate.ts per-property climate HTML extract ×N (≤100, concurrent) — preserves order, per-row available:false read
redfin_get_area_climate_baseline tools/climate.ts climate HTML extract over 2–10 sample URLs → averaged baseline + shared cluster_id read
redfin_get_comparable_rentals tools/rentals.ts GET /stingray/api/home/comparable-rentals?propertyId=…&rentEstimateLow=…&rentEstimateHigh=… read
redfin_get_saved_homes tools/saved.ts (a) GET /myredfin/favorites HTML → regex propertyIds(b) GET /stingray/do/api/v3/favorites/homecards?b=<csv-ids> — image URLs constructed locally from mlsId+dataSourceId read (auth)
redfin_get_saved_searches tools/saved.ts GET /myredfin/saved-searches HTML → regex region URLs read (auth)
redfin_calculate_mortgage tools/mortgage.ts (local; no network) read
redfin_calculate_affordability tools/affordability.ts (local; no network) read
redfin_healthcheck tools/healthcheck.ts GET /robots.txt round-trip through fetchproxy + bridge status incl. the extension link (session_state / pending_pair_code / extension_connected) — the shared registerBridgeHealthcheckTool from @chrischall/mcp-utils/fetchproxy read
redfin_register_session tools/sessions.ts (local; no network) — params: account_identity (required, min 1), auth_expires_at? write (registry)
redfin_set_active_session tools/sessions.ts (local; no network) — param: session_id write (registry)
redfin_get_session_context tools/sessions.ts (local; no network) — no params read

Read the full file on GitHub · 199 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.

  1. 3d ago Changed · +4 lines · +338 tokens per session d10eb656ae80
  2. 4d ago Changed · +3 lines · +85 tokens per session 59476fede4b8
  3. 8d ago First seen · 192 lines · 4,042 tokens per session scan A 4e014582351a

Subscribe to this mod's changes

redfin-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/redfin-mcp (3 stars, last pushed 3d ago), licensed MIT. It adds 4,465 tokens to every session, about $0.0223 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.

Related

Other instructions, from other repositories

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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens