How wealth managers and family offices value a client's collectible holdings
A client's statement of net worth lists a watch collection, two or three cars, a jewelry box and a wine cellar. Too often they sit at a round number someone wrote down years ago, or at an insured value that was never a market value. When you build a net-worth statement, review an estate or set an allocation to real assets, you need figures that are current and that you can defend, and “the dealer mentioned” is not a citation.
Connect the ALT/FNDATA connector to the assistant you already use, then ask for market statistics, a single-item price check, or a multi-year trend in plain language. Each answer is built from realized auction sales and carries the auction house, the sale date and a link, so the number goes straight into your working papers with its source attached.
One connector, your own assistant, plain-language questions
The ALT/FNDATA connector plugs auction price data into Claude, ChatGPT, Gemini, Perplexity and other assistants that support MCP. You ask in ordinary language and the assistant calls the right read-only tool for you. It covers 20 categories, from watches and jewelry to cars, fine art and wine, drawn from 650+ auction houses and normalized to USD. The tools only read: nothing in a client file is sent anywhere, and every result comes back with the sale it is based on.
A valuation pass across a mixed collection
Work one asset class at a time. Start broad to frame the segment, then narrow to the specific item, then show how the market has moved. The three tools below do most of the work.
Frame the segment with market statistics
A realized-price summary for that segment: the number of sold lots, the median, the 25th and 75th percentiles, the average, the minimum and maximum, the span of sale dates, and the auction houses that sold the most by volume.
This tells you where a typical piece sits and how wide the range is before you value any one item.
Price-check the specific item
A fair-value range for that one item, built from comparable realized sales, with the comparables listed and a confidence label. A well-specified reference returns a tight range and a high confidence; each comparable links to the sale it came from.
Show how the market moved
Realized prices bucketed by year (or quarter, or month), with the count and median per period, so you can see direction and depth. This is the chart that answers “is this holding up or softening?” in a review.
Reach an unusual holding across the whole market
A keyword search across every category at once, merged by realized price, for the pieces that match. Useful when a holding does not sit neatly in one table, or when you want to see comparable results wherever they sold.
Confidence, caveats and why the number is defensible
loose_key and reads low, because the pool it matched is broad. A genuinely wide spread of realized prices is flagged wide_quality_range and capped down, even when the item was well specified. Treat a low-confidence range as a prompt to add detail or to fall back on market_stats, not as a precise figure. Because every comparable carries the auction house, the sale date and a link, the number is defensible: you can footnote exactly which sales support it.What the data does and does not cover
The connector is a strong primary source for market evidence, within clear boundaries. Note these in your working papers.
- It reports realized auction results, what items actually sold for under the hammer, not retail list prices or private-treaty sales.
- For single-item fair-value ranges, live comparables cover handbags, watches and cars. For jewelry, gems, art, wine and the other categories, use
market_statsandsearchto assemble the comparable set. - Colored-stone single-item comparables are held back, so for a gemstone or a gem-set piece lean on
market_statsover the gems and jewelry segments rather than a single price check. - Unsold lots are tracked separately from sold ones, so a summary of realized prices reflects pieces that actually changed hands.
- It is market evidence for a valuation, not a formal appraisal or personalized investment advice.
Connect it once, then ask in plain language
Using the connector requires a paid ALT/FNDATA API key. Get one in the app, add the connector to your assistant with the setup page for your tool, then ask the questions above.
Questions
Frequently asked questions
Do I need to be technical to use this?
Is my client data sent anywhere?
Are these realized prices or estimates?
Can I cite these numbers in a client report?
Is there a free version?
Put a sourced number on it today.
Connect the ALT/FNDATA connector to the AI assistant you already use, and pull realized auction comparables, market statistics and price trends in plain language, each with a link to the sale.
The ALT/FNDATA connector is read-only and returns realized auction results across 20 categories from 650+ auction houses, normalized to USD, each with the auction house, sale date and a source link. It reports what items sold for at auction, not retail or private-treaty prices. Methodology · All datasets · All guides