mcpField
M
mostexpensivewatches

mostexpensivewatches

Remote
mostexpensivewatches.netGames & Entertainment0Updated 12w ago

About mostexpensivewatches

MostExpensiveWatches provides sourced data on luxury-watch auctions for AI agents, CLI users, and application developers. It combines an MCP server with an API, datasets, and a CLI for querying auction results, valuations, and market information.

Key features

  1. 01Search watch auction records and prices
  2. 02Find auction comparisons and market estimates
  3. 03Browse brand details and upcoming auctions
  4. 04Provides 43 API endpoints
  5. 05Includes datasets and a Python CLI

Use cases

  1. 01Research auction prices for a watch reference
  2. 02Compare records and estimate market prices
  3. 03Query auction data from apps or agents

MCP support

The Streamable HTTP server uses JSON-RPC 2.0 to expose watch searches, reference lookups, auction comparisons, estimates, brand information, and statistics to MCP clients. No API key is required.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mostexpensivewatches.net/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

10
ParameterTypeRequiredDescription
brandstringNoBrand name e.g. 'Patek Philippe'
limitnumberNo
querystringNo
materialstringNoCase material e.g. 'Platinum'
complicationstringNoComplication e.g. 'Tourbillon'
max_price_usdnumberNo
min_price_usdnumberNo

Details

From the project README

MostExpensiveWatches — watch auction records API, dataset, MCP server & CLI

Documented ultra-luxury watch auction data ($100k–$31M realized prices, primary-sourced), free to use, built for AI agents, CLIs and apps. No API key required.

Live site: https://mostexpensivewatches.net

For AI agents — MCP server (one line of config)

{"mcpServers": {"mostexpensivewatches": {"url": "https://mostexpensivewatches.net/mcp"}}}

Streamable HTTP, JSON-RPC 2.0. Tools: search_inventory, lookup_reference, search_auction_comps, list_upcoming_auctions, get_market_estimate, get_brand_info, search_answers, get_site_stats. Install docs: https://mostexpensivewatches.net/mcp/install

Datasets (CC-BY 4.0, schema.org Dataset, refreshed automatically)

DatasetLive JSONSnapshot here
Record Ledger — every documented watch auction record (all-time, per brand/material/year, record progressions)/data/records.jsondata/records.json
Auction Records — 1,150+ documented hammer prices with sources/api/auctions-dataset.jsondata/auction-records.json
Grail Index — the $1M+ segment record (182 results, $616M documented)/data/grail-index.jsondata/grail-index.json
Price Index — daily repeat-listing index across merchants/data/watch-price-index.jsondata/price-index.json

Snapshots in this repo are point-in-time copies; the live endpoints recompile daily via an autonomous verification pipeline. Cite as "MostExpensiveWatches Record Ledger".

API (43 endpoints, no key)

curl -s "https://mostexpensivewatches.net/api/listings/search?q=nautilus&limit=3"
curl -s "https://mostexpensivewatches.net/api/auctions?brand=Rolex&limit=5"
curl -s "https://mostexpensivewatches.net/api/answers/patek-5711-market-price.json"

CLI (dependency-free Python)

curl -sO https://mostexpensivewatches.net/cli/mew.py
python3 mew.py search "daytona" --limit 5

Also in this repo: mew.py

Human surfaces the data powers

License

Data: CC-BY 4.0 (attribution: MostExpensiveWatches). Code (mew.py): MIT.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.