arv-mcp
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
arv-mcp
An MCP server that estimates a home's after-repair value (ARV) from nearby sold comps, and hands the model the scored evidence behind the number so it can explain, check and challenge it.
Ask Claude "What's the ARV of 1234 Main St?" and it gets back a typical value, a renovated range, a confidence tier, the comps that support it (and the ones that were thrown out, with reasons), what's listed nearby right now, and warnings about anything that should make it cautious.
You: What's the ARV of 1234 Main Street?
Claude: Typical value is about $516k ($263/sqft on 1,961 sqft), based on
20 eligible sales, 5+ of them within a quarter mile (confidence 5/5).
Renovated comps support $541k–$586k. The closest match, 1260 Main
Street, sold 23 days ago for $465k ($272/sqft): same subdivision,
a bit smaller, no pool.
Worth knowing: this house itself sold this week for $432,500
($220/sqft), well under the comp-based value. That usually means it
sold in rough condition, which fits a flip at the renovated range.
Two of the eligible comps were distressed sales; without them the
median barely moves.Not an appraisal. Data comes from public listings on Realtor.com via HomeHarvest and can be wrong or missing. Use it for research and as a starting point, not for lending or legal decisions.
How it works
address ──► verify the property ──► sold comps ──► score & gate ──► estimate
│ (any status) within 1.5 mi each comp + evidence
└─ not verified? ──► locate it + ask for its factsFind the subject. The address is resolved to Realtor.com's record for exactly that street and unit, whether it's for sale, pending, sold or off market. Realtor.com's geocoder will happily return the wrong house for a bad address, so every result is checked against the street and unit typed. If nothing verifies, the address is located (Census geocoder, or caller-supplied lat/lon) and the tool asks for the facts it needs (
sqft,property_type) instead of guessing.Pull comps around the subject's coordinates: sold in the last 180 days within 1.5 miles (both adjustable per call), ±40% of the subject's size, same property type. The subject's own sale is pulled out and reported separately, so a just-sold house can't comp itself.
Score every comp on 13 factors: size, year built, lot, beds/baths, property type, recency, condition signals, distance, subdivision, garage, stories, pool and basement. Each known factor also has a floor. A comp that fails any one (a different property type, a much bigger house, one built decades apart) is excluded outright, however good it looks elsewhere. Size, age and lot floors loosen for comps right next door and tighten with distance.
Check the micro-market. Each comp's subdivision median (or its own $/sqft) must sit within ±20% of the subject's local price level, so a great physical match in a pricier pocket doesn't inflate the estimate. Subdivisions come from the MLS "Subdivision" field, with phases like "Unit 2" or "Ph 04 Sec 01" merged.
Estimate:
Typical value: similarity-weighted median $/sqft × subject sqft.
Renovated range: weighted 75th–90th percentile, what the top of the pool supports.
Confidence 1–5: how close the supporting comps are.
If no comp survives, the tool falls back to the area's going rate and says plainly that the number isn't comp-backed.
Related MCP server: DealScore MCP
Tools
get_arv
Parameter | Description |
| Full street address, including any unit number. |
| Override the record. Required when the address can't be verified. |
| Override or supply facts; also how what-ifs work ("what if it had a pool?"). |
| Locate a property no geocoder can find. |
| Comp search window: 0.25–5 mi (default 1.5), 30–730 days (default 180). |
| Also fetch nearby active/pending listings (default true). |
| Eligible comps to return, 1–25 (default 10). |
Returns subject, estimate (arv, renovated_range, arv_fallback,
window), confidence, pool_stats, eligible_comps (each with the factors
that cost it points and any distress flags), excluded_comps (with
reasons), market_context and guidance. Unknown facts are null, never
0.
Comps map
In hosts that support MCP Apps
(for example Claude on the web and desktop), get_arv also opens an
interactive map next to the answer:
the subject as an orange home pin
sold comps as price tags: green ⭐ for comps that fed the estimate, blue for the rest
active and pending listings as teal 🏠 and purple ⏳ tags, with ⭐ when they would qualify as comps
a popup on every tag with its facts and, for comps that weren't used, the reason
Street/Satellite basemaps, a "Sold within" filter (3M, 6M, 1Y, All) and a layer toggle for active/pending listings
The map gets its data through an app-only tool, get_comp_map, which the
model never sees. Opening it reuses get_arv's cached data, so it costs no
extra requests. Clients without MCP Apps support just get the normal
get_arv result.
lookup_property
The verified record for an address: size, beds/baths, year, lot, stories, garage, pool, subdivision, status, list price (only while it's on the market) and last sale.
Prompt: analyze_arv
An appraiser-style walkthrough (subject → comps → adjustments → range). Shows up as a slash command in Claude Code.
Errors
Failures come back as {"error": {"code", "message", ...}} so the model
can act on them:
Code | Meaning |
| Located, but no record matches; |
| Couldn't find or locate the address. |
| The record lacks something the estimate needs (e.g. sqft). |
| Vacant land: no living area to price per sqft. |
| No sales in the window; try a larger |
| Local rate limit; |
| Realtor.com refused or failed the request. |
Install
Claude Desktop: one-click install (recommended)
Download
arv-mcp.mcpbfrom the latest release.Double-click it, or drag it into Claude Desktop's Settings → Extensions, and click Install.
That's it: no terminal, no config file, and nothing else to install. Claude Desktop sets up Python and the dependencies itself; the first launch takes about half a minute while it does.
For developers
Requires Python 3.11+. Published on PyPI
and listed in the MCP Registry as
io.github.mariov7757/arv-mcp.
Claude Code
claude mcp add arv-mcp -- uvx arv-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"arv-mcp": {
"command": "uvx",
"args": ["arv-mcp"]
}
}
}pip
pip install arv-mcpTo run the unreleased main branch instead, use
uvx --from git+https://github.com/mariov7757/arv-mcp arv-mcp.
From a clone
git clone https://github.com/mariov7757/arv-mcp && cd arv-mcp
python -m venv .venv && .venv/bin/pip install -e ".[dev]"
claude mcp add arv-mcp -- "$PWD/.venv/bin/arv-mcp"Windows: if uvx fails installing pywin32 (os error 32 /
"being used by another process", usually antivirus scanning uv's temporary
build folder), install into a regular virtualenv instead and point the
client at the installed executable:
uv venv $HOME\.arv-mcp
uv pip install --python $HOME\.arv-mcp\Scripts\python.exe arv-mcp
claude mcp add arv-mcp -- $HOME\.arv-mcp\Scripts\arv-mcp.exeConfiguration
All optional, via environment variables:
Variable | Default | |
|
| Realtor.com requests per minute (token bucket)… |
|
| …and how many can go at once. |
|
| Census geocoder requests per second. |
|
| Longest a call waits for a rate-limit slot before returning |
|
| Tool calls processed at once. |
|
| Logs go to stderr. |
A full get_arv makes 5 requests to Realtor.com (2 to look up the subject,
1 for sold comps, 2 for active/pending) and takes ~4–6 s. Results are cached
for 15 minutes, so follow-ups and what-ifs on the same address return
instantly.
Limitations
Tuned on Phoenix metro. Gate bands and confidence tiers were calibrated on ~8,000 Phoenix-area valuations. The engine runs anywhere in the US, but in other markets (especially rural or low-volume ones) lean on the comps and confidence tier, and widen
radius_mi/days_back.Typical value isn't condition-aware. Distressed sales are flagged (MLS REO/short-sale conditions, "fixer"/"as-is" language) and their effect on the median is reported, but they aren't excluded.
$/sqft is the wrong tool for some properties. Land is refused; farms, multi-family and mobile homes get a warning.
Unofficial data source. HomeHarvest scrapes Realtor.com's public site. Requests run from your own machine and are rate-limited, but the site can change or block access at any time.
homeharvestis pinned to a tested range because the client relies on its internals.
Development
pip install -e ".[dev]"
pytest # offline suite; real network calls are blocked
ARV_MCP_LIVE_ADDRESS="<a real address>" pytest -m live # smoke tests against Realtor.com + Census
ruff check src testssrc/arv_mcp/
server.py MCP tools, instructions and prompt
service.py address in, estimate + evidence out
arv.py eligibility, weighted median, renovated range, confidence
scoring.py per-comp gated scoring
comps.py comp normalization and bad-data filters
ratelimit.py token buckets
data/client.py Realtor.com transport over HomeHarvest
data/homeharvest.py subject lookup, comp searches, field extraction
data/geocode.py Census geocoderReleasing
The version lives in one place: __version__ in src/arv_mcp/__init__.py.
Bump
__version__(patch for fixes, minor for new tools, parameters or fields) and merge tomainwith CI green.Tag the release and push the tag:
git tag v0.2.0 git push origin v0.2.0
The Release workflow then:
checks that the tag matches
__version__runs lint and tests, and builds the package
publishes to PyPI with Trusted Publishing (no API token)
stamps the version into
server.jsonand publishes it to the MCP Registry asio.github.mariov7757/arv-mcp, authenticated by GitHub OIDCbuilds the Claude Desktop extension (
arv-mcp.mcpb, seescripts/build_mcpb.py), validates it with the officialmcpbCLI, and attaches it to a GitHub Release
To build the extension locally (needs uv):
python scripts/build_mcpb.py, which writes dist/arv-mcp.mcpb.
PyPI versions are permanent. A broken release gets yanked on PyPI and replaced by the next patch version; a version number is never reused.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Address in. Defendable offer out. 60 seconds. Comps, ARV, repairs and max offer for any address.
- Homesage.ai MCPDeprecatedai.homesage
Estimated values, comps, rent, rehab costs and returns for 160M+ US properties, as 30+ agent tools.
Get automated U.S. residential home value reports with estimated value ranges and confidence, comparable sales, rent estimates, property facts, market forecasts and branded PDFs.
U.S. real-estate data: property records, AVM value + rent estimates, sale/rental listings.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides access to comprehensive US property data, including automated valuations, tax history, comparable sales, and ownership details, enabling real estate analysis and market insights.90 npmMIT
DealScore MCPDeprecated
FlicenseNot gradedqualityBmaintenanceEnables agents to evaluate car deals by returning a deal grade, numeric score, market price comparison, comps summary, risks, and confidence from a VIN or vehicle attributes without scraping listings.-- AlicenseNot gradedqualityCmaintenanceEnables US address verification and standardization, validating deliverability and returning USPS-standardized data, plus property enrichment with 350+ tax assessor and deed attributes for a given address.282 npmMIT
- AlicenseBqualityBmaintenanceEnables multifamily renovation cost estimation, scope of work generation, contractor bid evaluation, ROI gating, and risk flagging for real estate intelligence agents.11Apache 2.0