What is onehome-mcp CLAUDE.md?

A repository guide for working on OneHome MCP, a tool server for a private real-estate portal. It explains how the portal's login link, session token, GraphQL service, and REST endpoints work.

Use it when developing or maintaining integrations that fetch property and related data from the OneHome portal.

The portal is not a normal public website, so ordinary web requests are not enough. The guide explains how authenticated requests and the emailed access link are handled.

How chrischall/onehome-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to chrischall/onehome-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/onehome-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/chrischall/onehome-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/onehome-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/chrischall/onehome-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/chrischall/onehome-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/onehome-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/chrischall/onehome-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/chrischall/onehome-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,897 This file is loaded in full into every session.

When invoked 5,897 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.05897	$0.05897
Opus 5	$0.02949	$0.02949
Sonnet 5	$0.01179	$0.01179
Haiku 4.5	$0.00590	$0.00590

Measured 4d ago against content hash 7b2fb33405a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

onehome-mcp CLAUDE.md scanned grade A with 0 findings 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 4d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — onehome-mcp

Guidance for Claude working in this repo.

TL;DR

OneHome (CoreLogic) MCP server. OneHome isn't a public realty site — buyers reach it through a private "magic link" their real-estate agent emails (https://portal.onehome.com/...?token=eyJ...). The portal is an Angular SPA backed by services.onehome.com/graphql (real GraphQL) plus a few services.onehome.com/api/... REST endpoints (LocalLogic schools/scores, the token-exchange bootstrap). All authenticated requests go through Authorization: Bearer <sessionToken>.

So onehome-mcp departs from the Pattern A / Pattern B fetchproxy split the other realty MCPs use. Every tool call is a direct Node fetch to services.onehome.com with an Authorization: Bearer <sessionToken> header attached. The interesting parts are where the bearer comes from and the email-token → sessionToken bootstrap:

ONEHOME_TOKEN — raw bearer pasted from devtools. If it's a 3-segment JWT we use it directly; if it's a 1-segment base64 blob (the URL ?token=... shape) we exchange it (#2 below).
ONEHOME_MAGIC_LINK — the full portal URL with ?token=.... We extract the token query param, recognize it as an email-token (single base64 segment carrying { OSN, contactid, agentid, setid, … }), and POST it to POST /api/authentication/checkToken { emailToken } to get back a real sessionToken JWT — plus the consumer's group / savedSearch / agent scope, which the MCP caches and uses to default unspecified group_id / saved_search_id arguments.
fetchproxy captureRequestHeader — bring up a @fetchproxy/server bridge on 127.0.0.1:37149 and wait for the user's signed-in portal.onehome.com Chrome tab to fire any GraphQL request; snapshot its Authorization header (which is already a Bearer <sessionToken> post-exchange), cache it, then make direct outbound calls from Node.

Once the bearer is acquired we don't route subsequent calls through fetchproxy — there's no anti-bot challenge to dodge at services.onehome.com, so the round-trip through the tab would just add latency and a bridge-down failure mode.

Read the full file on GitHub · 237 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.

4d ago Changed · +4 lines · +495 tokens per session 7b2fb33405a6
9d ago First seen · 233 lines · 5,402 tokens per session scan A cb2d175b09d2

Subscribe to this mod's changes

onehome-mcp CLAUDE.md is an instructions file published in the GitHub repository chrischall/onehome-mcp (1 stars, last pushed today), licensed MIT. It adds 5,897 tokens to every session, about $0.0295 per session on Opus 5. A static security scan graded it A with 0 findings. 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

onehome-mcp: Instructions file for Claude Code