Skip to main content
Glama

Gold Hub: live gold, its market value and where the money goes when gold is sold

get_gold
Read-only

The OwlChart Gold Hub in one tool (v5.890): what=market (gold futures GC=F and spot XAU/USD, change against yesterday's close, day high and low, the highest trade and its date, 7 day, 30 day, 1 year and year to date moves, gold/silver, market open or closed, the gold miners and the PAXG and XAUT premium), brief (the facts, the strings the page prints, a plain read, the headline), rotation (days=90 or 30: for the dollar, yields, T-bills, bonds, metals, oil, stocks, crypto and the VIX, today's move, the average move and the share of days it rose on the days gold fell hard, a plain label RECEIVING, SOLD WITH GOLD or NEUTRAL, the 30 and 90 day correlation word, today's ranked receivers and the markets sold together with gold), flows (tokenised gold PAXG and XAUT supply and the day's mint or burn read from the Ethereum contracts, CFTC managed money net long in COMEX gold, spot Bitcoin fund flows, stablecoins issued or redeemed, the central bank figure when entered), ratios (gold/silver, ounces of gold per Bitcoin, gold/S&P 500, gold/oil, gold/copper, each with its five year range), value (all the gold above ground in dollars, the change today, from the 90 day high, this year and from the highest trade, against Bitcoin, all crypto and US M2), rates (US 10 year yield, the 10 year real yield from treasury.gov, the dollar index, the next Fed meeting and odds) news (gold, Fed, dollar and central bank headlines), crypto (v5.892, is gold money reaching crypto: the verdict NOT RECEIVING, STARTING or RECEIVING with a 0 to 100 gauge and its seven signs as ticks, gold fund flows against Bitcoin fund flows in dollars from the files of the issuers, the Gold to Bitcoin days in 30 and 90 days, stablecoins, the Coinbase and Upbit premiums, spot taker netflow, T-bill fund flows, today hour by hour in one sentence, the size of the prize and what Bitcoin did after each past RECEIVING day), bitcoin (v5.894, gold against Bitcoin over one year: both prices with the move today, over 30 days and 1 year, ounces of gold for one Bitcoin and its change, the 30 and 90 day correlation, what Bitcoin did on the days gold fell hard), investor (v5.893, the whole long-term picture in one call: price, market value, valuation percentiles, fund holdings and flows, futures positioning, central banks, the crypto verdict, correlations and the ways to own gold), valuation (gold in today's dollars after US inflation, the percentile of the price, the real price and gold/S&P 500 against their own history, returns, deepest fall and yearly swing over 1, 5, 10 and 20 years; a percentile, never a view on cheap or expensive), cot (CFTC gold futures: managed money, swap dealers and producers, net in contracts and tonnes, open interest, the 5 year percentile of the fund position), etf (GLD, GLDM and IAU: tonnes, assets, money in or out over the day, 5 and 21 days, from the issuers), own (five ways to own gold side by side and the prices for the calculator) or reserves (v5.891, who holds the gold: the official gold of every country from the IMF International Liquidity file in tonnes, its value at the live price, percent of reserves, last month and twelve month change, the month it is for and the day first seen, with the header totals, net central bank buying over 1, 3 and 12 months, top buyer and seller and the dip buyers; give country as a three letter ISO code, for example POL, for one country with its full history and a plain read; reserves are reported monthly and late, not live). Moving together is not proof that money moved from one market to another. Page: owlchart.com/gold.html. Data, not advice.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_gold"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNorotation: the window in days, default 90
whatNowhich gold data set, default brief
countryNoreserves: a three letter ISO country code for one country, or leave empty for the summary and the top 25

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / what / enum
      Previous value: -[
      -  "market",
      -  "brief",
      -  "rotation",
      -  "crypto",
      -  "flows",
      -  "ratios",
      -  "value",
      -  "rates",
      -  "news",
      -  "reserves"
      -]New value: +[
      +  "investor",
      +  "market",
      +  "brief",
      +  "rotation",
      +  "crypto",
      +  "bitcoin",
      +  "valuation",
      +  "cot",
      +  "etf",
      +  "own",
      +  "flows",
      +  "ratios",
      +  "value",
      +  "rates",
      +  "news",
      +  "reserves"
      +]
  2. Added

TDQS

A3.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: reserves are 'reported monthly and late, not live', valuation is 'a percentile, never a view on cheap or expensive', and the correlation caveat that 'moving together is not proof that money moved'. It stops short of describing response shape or error behavior, but the domain caveats are the valuable part.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Everything is crammed into one dense paragraph with no line breaks or grouping, making the sixteen sections hard to scan. Version tags like '(v5.890)', '(v5.892)' and the page URL consume space without helping an agent decide or call the tool, and the enumeration is repetitive in places.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and sixteen selectable data sets, the description carries the full burden of explaining returns and does so thoroughly for every 'what' value, including defaults implied by the schema. The only omissions are freshness/rate expectations for the live sections and any sense of payload size.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both enums are structurally documented, so the baseline would be 3. The description earns above that by explaining what each 'what' value actually returns (e.g. 'cot' = CFTC managed money, swap dealers and producers net in contracts and tonnes; 'reserves' expects a three-letter ISO code like POL for one country and returns the top 25 otherwise), adding meaning the enum names alone do not convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (OwlChart Gold Hub) and enumerates the sixteen data sets the single tool exposes via the 'what' enum, so an agent can tell it apart from siblings like get_etf_flows or get_money_flows. It is a clear one-stop gold tool, though the goal statement is buried under an extremely long enumeration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the 'one tool' framing and by per-section hints such as 'investor (the whole long-term picture in one call)', which helps route an agent. However, no alternative tool is ever named and no when-not-to-use condition is given, even though etf, flows and reserves clearly overlap with sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources