# ARV Estimator (pypi · arv-mcp)

Estimate a home's after-repair value from scored, gated sold comps, with the evidence.

- Trust score: 79/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `arv-mcp`: 79/100 (this document), [markdown](https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp.md), [page](https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp)

## Channel facts

- Registry: `pypi`
- Package: `arv-mcp`
- Version: `0.2.2`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 39 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to mariov7757/arv-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 70/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1172 tokens (~293/item across 4 items; 3 tools + 1 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 55% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the ARV Estimator MCP server?

ARV Estimator runs locally as a PyPI package, launched with uvx arv-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add mariov7757-arv-mcp -- uvx arv-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "mariov7757-arv-mcp": {
      "command": "uvx",
      "args": [
        "arv-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mariov7757-arv-mcp": {
      "command": "uvx",
      "args": [
        "arv-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add mariov7757-arv-mcp -- uvx arv-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mariov7757-arv-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "arv-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mariov7757-arv-mcp --command uvx --arg arv-mcp
```

### Hermes

```yaml
mcp_servers:
  mariov7757-arv-mcp:
    command: "uvx"
    args: ["arv-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "mariov7757-arv-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "arv-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add mariov7757-arv-mcp -t stdio -c uvx -a arv-mcp
```

### Other

```json
{
  "mcpServers": {
    "mariov7757-arv-mcp": {
      "command": "uvx",
      "args": [
        "arv-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-31 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-30 (score 64)

First indexed and scored.

## MCP tools (3)

### `get_arv` (~752 tokens)

Estimate ARV from sold comps

Estimate a property's value from nearby sold comps and return the evidence.

How to use the result:
\- estimate.arv is TYPICAL value (similarity-weighted median of eligible sold
  comps' $/sqft x subject sqft). estimate.renovated_range is what the top of
  the eligible pool supports, i.e. the ARV a flip finished to the top of the
  neighbourhood could target. Quote both, labelled. If renovated_range is
  null, say there weren't enough comps to separate renovated sales.
\- Treat the estimate as one input: check it against the closest, highest-
  scoring eligible_comps and say whether they agree. Use each comp's
  \`factors` to explain differences (size, age, pool...).
\- Read `guidance` first and pass its warnings on. In particular:
  arv_fallback=true means NOT comp-backed; low confidence.tier (1-2) means
  thin evidence; distressed comps (REO/short sale) pull prices down; a
  subject_source of "user_supplied" means the facts weren't verified.
\- market_context is current asking prices, a ceiling check only, never comps.
\- If subject.address differs from what the user asked (address_fuzzy_match),
  confirm it's the right property.
\- For what-ifs ("what if it had a pool / were 1,800 sqft"), call again with
  that fact overridden; cached data makes repeat calls fast.

Errors come back as {"error": {"code", "message", ...}}:
\- ADDRESS_NOT_VERIFIED: the address was located but no record matches it.
  Ask the user for the facts in `needs` (and ideally `recommended`), then
  call again with them.
\- ADDRESS_NOT_FOUND: ask the user to check the address, or pass latitude and
  longitude with the facts.
\- MISSING_FACTS: ask for the listed facts and call again.
\- UNSUPPORTED_PROPERTY_TYPE (vacant land), NO_COMPS (try a larger radius_mi
  or days_back), RATE_LIMITED (wait retry_after_s), UPSTREAM_ERROR (data
  source unavailable): explain to the user.

Input parameters:

- `address` (string, required): Full street address, e.g. '1234 E Main St, Mesa, AZ 85204'. Include the unit number for condos/townhomes.
- `baths`: Bathrooms, halves as .5 (override).
- `beds`: Bedrooms (override).
- `days_back`: How far back to look for sales, in days (30-730, default 180).
- `garage`: Garage spaces (override).
- `has_pool`: Private pool (override).
- `include_market_context` (boolean): Also fetch nearby active/pending listings (two extra requests).
- `latitude`: Only when the address can't be located; pass with longitude.
- `longitude`: Only when the address can't be located; pass with latitude.
- `lot_sqft`: Lot size in sqft (override).
- `max_comps`: How many eligible comps to return (1-25, default 10).
- `property_type`: single_family, condo, townhome, multi_family, mobile, farm or land. Required when the address can't be verified.
- `radius_mi`: Comp search radius in miles (0.25-5, default 1.5). Widen for rural or thin markets.
- `sqft`: Living area sqft. Overrides the record; required when the address can't be verified.
- `stories`: Levels in the unit (override).
- `year_built`: Year built (override).

### `get_comp_map` (~134 tokens)

Comps map data

Comps-map data for the get_arv map view: the subject and every sold comp and
active/pending listing with coordinates and marker/popup HTML. Called by the
map itself, not by the model.

Input parameters:

- `address` (string, required)
- `baths`
- `beds`
- `days_back`
- `garage`
- `has_pool`
- `latitude`
- `longitude`
- `lot_sqft`
- `property_type`
- `radius_mi`
- `sqft`
- `stories`
- `year_built`

### `lookup_property` (~107 tokens)

Look up a property's facts

Look up the verified Realtor.com record for an address: size, beds/baths,
year built, lot, stories, garage, pool, subdivision, status, list price (when
on the market) and last sale. Works for sold, off-market and for-sale homes.
Returns ADDRESS_NOT_VERIFIED / ADDRESS_NOT_FOUND errors when no record matches
the exact street and unit. Use get_arv for valuations.

Input parameters:

- `address` (string, required): Full street address, including any unit number.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp#diagnostics

## Score history

- 2026-11-05: 79
- 2026-11-04: 79
- 2026-11-03: 79
- 2026-11-02: 79
- 2026-11-01: 79
- 2026-10-31: 79
- 2026-10-30: 64

## Common questions

### What is the ARV Estimator MCP server?

ARV Estimator is an MCP server listed in the public MCP registry as io.github.mariov7757/arv-mcp. Estimate a home's after-repair value from scored, gated sold comps, with the evidence. This page covers its PyPI package (arv-mcp).

### Is the ARV Estimator MCP server safe to use?

ARV Estimator scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the ARV Estimator MCP server expose?

ARV Estimator exposes 3 tools: get_arv, get_comp_map, lookup_property. Their descriptions and schemas cost roughly 993 tokens of context every time the server is loaded.

### Is the ARV Estimator MCP server still maintained?

ARV Estimator is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the ARV Estimator MCP server under?

ARV Estimator declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/arv-mcp/
- Socket report: https://socket.dev/pypi/package/arv-mcp
- Repository: https://github.com/mariov7757/arv-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mariov7757-arv-mcp/arv-mcp