# ATLAS Explain (remote · atlas-explain-mcp.atlas-explain.workers.dev)

Market jargon in plain language: terms, official figures, crypto prices and charts, headlines.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `atlas-explain-mcp.atlas-explain.workers.dev`: 71/100 (this document), [markdown](https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp.md), [page](https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp)

## Channel facts

- Endpoint: `https://atlas-explain-mcp.atlas-explain.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.20.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 88/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 5546 tokens (~61/item across 90 items; 21 tools + 69 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 21 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 23 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.

## Install

### How do I install the ATLAS Explain MCP server?

ATLAS Explain is a hosted endpoint at https://atlas-explain-mcp.atlas-explain.workers.dev/mcp, so there is nothing to install locally. 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 --transport http mishhf93-atlas-explain 'https://atlas-explain-mcp.atlas-explain.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "mishhf93-atlas-explain": {
      "url": "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mishhf93-atlas-explain": {
      "type": "http",
      "url": "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.mishhf93-atlas-explain]
url = "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mishhf93-atlas-explain": {
      "type": "remote",
      "url": "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mishhf93-atlas-explain --url 'https://atlas-explain-mcp.atlas-explain.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mishhf93-atlas-explain:
    url: "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "mishhf93-atlas-explain": {
      "Transport": "http",
      "Url": "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add mishhf93-atlas-explain -t streamable-http -u 'https://atlas-explain-mcp.atlas-explain.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "mishhf93-atlas-explain": {
      "type": "http",
      "url": "https://atlas-explain-mcp.atlas-explain.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-20 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 70, 0)

- [functional regression] Schema quality: 4349 → 5546
- [functional regression] Schema quality: 4349 → 5248
- [functional] New resource “apr_apy”
- [functional] New resource “asset_allocation”
- [functional] New resource “bear_market”
- [functional] New resource “brokerage_account”
- [functional] New resource “bull_market”
- [functional] New resource “capital_gain”
- [functional] New resource “compound_growth”
- [functional] New resource “diversification”
- [functional] New resource “dollar_cost_averaging”
- [functional] New resource “emergency_fund”
- [functional] New resource “expense_ratio”
- [functional] New resource “index_fund”
- [functional] New resource “mutual_fund”
- [functional] New resource “real_return”
- [functional] New resource “rebalancing”
- [functional] New resource “risk_tolerance”
- [functional] New resource “tax_advantaged_account”
- [functional] New resource “time_horizon”
- [functional] Server version: 1.19.0 → 1.20.0
- [functional] Server version: 1.17.0 → 1.19.0
- [functional] Server version: 1.16.0 → 1.17.0
- [functional] New tool “decision_explainer”
- [functional] New tool “speech_tracker”
- [functional] New tool “rate_change_impact”

### 2026-11-18 (score 70, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “explain_term” rewrote its description, which is the text the model reads
- [security] Tool “economic_calendar” rewrote its description, which is the text the model reads
- [security] Tool “economy_snapshot” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2402 → 4349
- [functional regression] Schema quality: 2402 → 3941
- [functional regression] Schema quality: 2402 → 3766
- [functional improvement] Tool coverage: 82% → 100%
- [functional improvement] Tool coverage: 82% → 88%
- [functional improvement] Tool “browse_glossary” now declares an output schema
- [functional improvement] Tool “explain_term” now declares an output schema
- [functional] New prompt “make_a_report”
- [functional] New prompt “whats_coming_up”
- [functional] New prompt “check_an_offer”
- [functional] New prompt “money_lesson”
- [functional] New prompt “whats_notable”
- [functional] New resource “coming-up”
- [functional] New resource “countries”
- [functional] New resource “data-series”
- [functional] New resource “evidence-brief”
- [functional] New resource “treasury-auctions”
- [functional] New resource “bond”
- [functional] New resource “central_bank”
- [functional] New resource “cpi”
- [functional] New resource “dividend”
- [functional] New resource “gdp”
- [functional] New resource “inflation”
- [functional] New resource “liquidity”
- [functional] New resource “market_cap”
- [functional] New resource “money-maths”
- [functional] New resource “notable-today”
- [functional] New resource “order_book”
- [functional] New resource “pe_ratio”
- [functional] New resource “policy_rate”
- [functional] New resource “recession”
- [functional] New resource “slippage”
- [functional] New resource “unemployment_rate”
- [functional] Server version: 1.15.0 → 1.16.0
- [functional] Server version: 1.13.0 → 1.15.0
- [functional] Server version: 1.9.0 → 1.13.0
- [functional] New tool “data_series”
- [functional] New tool “upcoming_events”
- [functional] New tool “compare_countries”
- [functional] New tool “money_maths”
- [functional] New tool “notable_today”
- [functional] New tool “scam_red_flags”
- [functional] New tool “treasury_auctions”
- [cosmetic] “economic_calendar” reworded the description of “bank”

### 2026-11-17 (score 69, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “asset_details” rewrote its description, which is the text the model reads
- [security] Tool “crypto_prices” rewrote its description, which is the text the model reads
- [security] Tool “economic_calendar” rewrote its description, which is the text the model reads
- [security] Tool “economy_snapshot” rewrote its description, which is the text the model reads
- [security] Tool “evidence_brief” rewrote its description, which is the text the model reads
- [security] Tool “market_depth” rewrote its description, which is the text the model reads
- [security] Tool “official_figures” rewrote its description, which is the text the model reads
- [security] Tool “price_history” rewrote its description, which is the text the model reads
- [security] Tool “todays_headlines” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 2156 → 2402
- [functional improvement] Stability: unverified → 0.03
- [functional] New prompt “brief_on_asset”
- [functional] New prompt “economy_today”
- [functional] New prompt “quiz_me”
- [functional] Server version: 1.7.0 → 1.9.0
- [functional] Server version: 1.6.0 → 1.7.0
- [functional] New tool “evidence_brief”

### 2026-11-16 (score 69)

First indexed and scored.

## MCP tools (21)

### `explain_term` (~78 tokens)

Explain a market term

The plain-language meaning of a market or economics term from ATLAS Explain's glossary, such as stop-limit order, yield curve, inflation or P/E. Use it when someone asks what a term means. Up to three closest terms, each with its glossary group. Education only.

Input parameters:

- `term` (string, required): The term or phrase to look up.

Output parameters:

- `found` (boolean)
- `learnUrl` (string)
- `notice` (string)
- `query` (string)
- `terms` (array)

### `browse_glossary` (~89 tokens)

Browse the glossary and learning path

List ATLAS Explain's learning path (topics in order, each with its terms) or every glossary term in one group. Use it to suggest what to learn next, or to find the right term to explain.

Input parameters:

- `topic` (string): Optional learning-path topic or glossary group, for example 'orders', 'risk', 'rates', 'futures'. Leave empty for the whole path.

Output parameters:

- `groups` (array)
- `notice` (string)
- `steps` (array)
- `topic` (string|null)
- `totalTerms` (number)

### `asset_details` (~112 tokens)

What an asset is

What one asset is, where and when it trades, and its latest official figure or price with source and time, or why no price is shown. Use it when someone asks about a specific coin, stock, ETF, currency, rate or index. Covers crypto, US stocks and ETFs, currencies, interest rates, energy, indices, futures and options.

Input parameters:

- `asset` (string, required): Name or symbol, for example 'Bitcoin', 'AAPL', 'EUR/USD', '10-year', 'S&P 500'.

Output parameters:

- `about` (string)
- `appUrl` (string)
- `asOf` (string|null)
- `assetClass` (string)
- `change` (number|null)
- `changePct` (number|null)
- `changeWindow` (string|null)
- `currency` (string)
- `facts` (array)
- `found` (boolean)
- `name` (string)
- `noPriceReason` (string|null)
- `notice` (string)
- `priceUsd` (number|null)
- `relatedTerms` (array)
- `source` (string|null)
- `sourceUrl` (string|null)
- `symbol` (string)
- `tenor` (string|null)
- `tradingHours` (string|null)
- `value` (number|null)
- `venue` (string|null)

### `official_figures` (~110 tokens)

Official market figures

Official figures with source and date: US Treasury yields, ECB and Bank of Canada rates, EIA energy prices, and SEC-filed company figures. Use it for rates, yields, exchange rates or a company's reported results. The SEC figures cover revenue, net income, earnings per share and shares outstanding for about 30 large US companies and ETFs. Optional search by name or symbol.

Input parameters:

- `query` (string): Optional name or symbol, for example '10-year', 'EUR', 'AAPL'.

Output parameters:

- `figures` (array)
- `notice` (string)

### `crypto_prices` (~142 tokens)

Crypto prices

Current prices and today's change for ten major coins, biggest moves first, with when they were collected. Use it for how crypto is doing today, or one coin's price. Coins: Bitcoin, Ethereum, Solana, XRP, Cardano, Dogecoin, Litecoin, Polkadot, Chainlink and Avalanche, each with its last 24 hours of hourly closes. Refreshed about every 10 minutes by ATLAS Explain's data job from Kraken's public market data (CoinGecko as backup) and served from ATLAS Explain's own data site.

Input parameters:

- `coin` (string): Optional coin name or symbol, for example 'BTC' or 'Ethereum'.

Output parameters:

- `coins` (array)
- `notice` (string)
- `source` (string)

### `price_history` (~115 tokens)

Crypto price history

How a coin moved over 24 hours, 7 days or 30 days: start, end, change, high and low with their times. Use it when someone asks how a coin moved or wants a price chart. From the hourly closes on ATLAS Explain's own data site (refreshed about every 10 minutes). Describes the past only; never a forecast.

Input parameters:

- `coin` (string, required): Coin name or symbol, for example 'BTC'.
- `range` (string): Time range. Default 7d.

Output parameters:

- `changePct` (number)
- `endUsd` (number)
- `high` (object)
- `low` (object)
- `name` (string)
- `notice` (string)
- `points` (array)
- `range` (string)
- `rangeLabel` (string)
- `source` (string)
- `startUsd` (number)
- `symbol` (string)

### `todays_headlines` (~116 tokens)

Today's market headlines

Recent market headlines and official press releases, each with publisher, link and time. Use it for what's in the news, optionally about one company or coin. Sources: official press releases from the Federal Reserve, SEC, CFTC, ECB, Bank of Canada and Bank of England, and the GDELT Project's news index. News stories older than 36 hours and releases older than 4 days are never returned.

Input parameters:

- `about` (string): Optional company, coin or word, for example 'Nvidia' or 'Bitcoin'.

Output parameters:

- `headlines` (array)
- `notice` (string)
- `refreshedAt` (string)

### `economy_snapshot` (~172 tokens)

The economy at a glance

Headline economic figures with period, change and source: inflation, unemployment, policy rates and US public debt, plus the next rate decisions. Use it for how the economy is doing, or one topic. Covers US CPI over 12 months and unemployment (Bureau of Labor Statistics), the effective federal funds rate with the Fed's target range and SOFR (New York Fed), euro-area inflation and the ECB deposit rate (ECB), Canada's policy rate (Bank of Canada), the UK's Bank Rate (Bank of England) and US public debt (Treasury), each with about a year of history. Optional filter by topic.

Input parameters:

- `topic` (string): Optional topic, for example 'inflation', 'jobs', 'rates', 'debt', 'euro' or 'canada'. Leave empty for all.

Output parameters:

- `indicators` (array)
- `nextEvents` (array)
- `notice` (string)
- `refreshedAt` (string)

### `economic_calendar` (~115 tokens)

Upcoming rate decisions

Dates of the next interest-rate decisions by the Federal Reserve, the European Central Bank, the Bank of Canada and the Bank of England, with what happens on the day. Use it for when the next Fed, ECB, Bank of Canada or Bank of England meeting is. From each bank's own published calendar. Dates only: it never guesses the outcome. Optional filter by central bank.

Input parameters:

- `bank` (string): Optional: 'Fed', 'ECB', 'Bank of Canada' or 'Bank of England'. Leave empty for all.

Output parameters:

- `events` (array)
- `notice` (string)
- `refreshedAt` (string)

### `market_depth` (~112 tokens)

Bid, ask and order book

A coin's best bid and ask, bid-ask spread, order-book depth, and the slippage of filling an order of a given size. Use it to explain spreads, liquidity or trading costs with real numbers. For the ten coins ATLAS Explain follows, from Kraken's public market data; the spread is refreshed every few minutes and the order book about every 10 minutes. Explains how markets work; never suggests a trade.

Input parameters:

- `coin` (string, required): Coin name or symbol, for example 'BTC'.

Output parameters:

- `askUsd` (number)
- `bidUsd` (number)
- `book` (object|null)
- `bookMidUsd` (number|null)
- `depth` (array)
- `impact` (array)
- `midUsd` (number)
- `name` (string)
- `notice` (string)
- `quoteAsOf` (string)
- `source` (string)
- `spreadBps` (number)
- `spreadPct` (number)
- `spreadUsd` (number)
- `symbol` (string)

### `evidence_brief` (~147 tokens)

Evidence brief on one asset

Everything ATLAS Explain knows about one asset on one page, each fact sourced, plus what the facts don't tell you. Use it when someone wants the full picture on a coin, company, currency or rate. Includes what it is, its latest figures or price, how it moved over 7 days and how easily it trades (coins), the economic backdrop and the next rate decision, headlines that name it, terms to know, and what people commonly look at for this kind of asset. Facts only: it never recommends, rates or forecasts anything.

Input parameters:

- `asset` (string, required): Name or symbol, for example 'Bitcoin', 'AAPL', 'EUR/USD' or '10-year'.

Output parameters:

- `asset` (object)
- `backdrop` (array)
- `facts` (array)
- `limits` (array)
- `liquidity` (object|null)
- `news` (array)
- `nextDecision` (object|null)
- `notice` (string)
- `recentMove` (object|null)
- `terms` (array)
- `weigh` (array)

### `notable_today` (~83 tokens)

What's notable today

What stands out in today's data, each with its source and the rule that picked it: unusual crypto moves, a flat or inverted yield curve, rate decisions this week, changed economic figures. Use it for what's happening or what's worth knowing today. Also lists new official releases and what was checked but found ordinary. Describes the past only; never a forecast or a suggestion.

Output parameters:

- `asOf` (string)
- `limits` (array)
- `notice` (string)
- `observations` (array)
- `quiet` (array)
- `unavailable` (array)

### `upcoming_events` (~131 tokens)

Coming up: decisions and data releases

The next scheduled market events with exact times and a countdown: Fed, ECB, Bank of Canada and Bank of England rate decisions and the US inflation, jobs and producer-price releases. Use it for what's coming up, or when the next CPI or jobs report or rate decision is. Each event has the latest related figure and 'if this happens' explainers for each possible outcome, from the banks' and the BLS's own calendars. It never says which outcome will happen. Optional filter: 'rates' or 'data'.

Input parameters:

- `only` (string): Optional: only rate decisions, or only data releases.

Output parameters:

- `events` (array)
- `notice` (string)
- `refreshedAt` (string)

### `money_maths` (~280 tokens)

Money maths

Works out compound growth, what a fee costs over the years, what inflation does to cash, or how holding more things changes how much a mix swings, from numbers the person gives. Use it to show how money grows or shrinks over time with their own example. Pure arithmetic, drawn as a chart they can change in Claude; the rate is their assumption, never a forecast or a suggestion.

Input parameters:

- `amount` (number): Starting amount (compound_growth, fees, inflation).
- `calculation` (string, required): Which calculation.
- `correlation` (number): How closely holdings move together, -1 to 1 (diversification).
- `fee_pct` (number): Yearly fee in percent of the balance (fees).
- `holdings` (number): Show up to this many holdings, 2 to 100 (diversification; default 20).
- `inflation_pct` (number): Yearly inflation to assume, in percent (inflation).
- `monthly` (number): Optional amount added each month (compound_growth, fees).
- `rate_pct` (number): Yearly return the person wants to assume, in percent (compound_growth, fees).
- `volatility_pct` (number): How much one holding swings in a year, in percent (diversification).
- `years` (number): Number of years, 1 to 60.

Output parameters:

- `calculation` (string)
- `inputs` (object)
- `lines` (array)
- `notice` (string)
- `series` (array)
- `xLabel` (string)
- `yLabel` (string)

### `scam_red_flags` (~123 tokens)

Investment scam warning signs

The warning signs of investment fraud regulators describe, which of them a message or offer shows, where to check a seller's registration and where to report, plus recent official fraud actions. Use it when someone asks whether an offer, message or 'opportunity' looks like a scam. It points out warning signs; it never says something is or isn't a scam, and the text given is not kept.

Input parameters:

- `pitch` (string): Optional: the message, ad or offer the person received, in their words or pasted. Leave empty for the full list of warning signs.

Output parameters:

- `allSigns` (array)
- `check` (array)
- `matched` (array)
- `notice` (string)
- `recentActions` (array)
- `report` (array)

### `treasury_auctions` (~123 tokens)

US Treasury auctions

Upcoming US Treasury auctions and the latest results: what is sold, how much, the yield it set and how much demand there was. Use it to explain how the US government borrows, or what bid-to-cover and auction yields mean. From TreasuryDirect, refreshed every 6 hours. Describes auctions that are announced or done; never predicts a result. Optional filter: bills, notes, bonds or TIPS.

Input parameters:

- `kind` (string): Optional: 'bills', 'notes', 'bonds' or 'TIPS'. Leave empty for all.

Output parameters:

- `notice` (string)
- `recent` (array)
- `refreshedAt` (string)
- `source` (string)
- `upcoming` (array)

### `compare_countries` (~153 tokens)

Countries compared

GDP growth, inflation, unemployment and GDP per person for the G20 countries and the EU, with the year of each figure, from the World Bank. Use it to compare economies or put one country's figures in context. Actual published values only (World Development Indicators, CC BY 4.0), updated daily; never a projection. Optional: one indicator and a list of countries.

Input parameters:

- `countries` (string): Optional: country names or codes separated by commas, for example 'Canada, Japan, Germany'. Leave empty for the whole G20.
- `indicator` (string): Optional: 'gdp growth', 'inflation', 'unemployment' or 'gdp per person'. Leave empty for all four.

Output parameters:

- `countries` (array)
- `indicators` (array)
- `notice` (string)
- `refreshedAt` (string)
- `source` (string)

### `data_series` (~193 tokens)

Data series for charts and reports

Clean dated rows of official economic data, with source and licence, for making a chart, spreadsheet, table or report. Use it when someone wants the numbers themselves, or to build something from them. Covers US inflation, unemployment, the fed funds rate, SOFR and debt, euro-area inflation, the ECB, Bank of Canada and Bank of England rates, and World Bank GDP growth, inflation, unemployment and GDP per person for the G20. Also returns CSV. Leave empty for the list. Never crypto or stock prices.

Input parameters:

- `countries` (string): For world_ series: up to six G20 country names or codes, for example 'Japan, Germany'. Defaults to the United States.
- `series` (string): Optional: one to four series ids or names, separated by commas, for example 'us_cpi, uk_bank_rate' or 'world_inflation'. Leave empty to list what's available.

Output parameters:

- `available` (array)
- `csv` (string)
- `notice` (string)
- `series` (array)

### `rate_change_impact` (~276 tokens)

What a rate change would do to my numbers

Works out what a change in interest rates would do to someone's own variable-rate mortgage payment, HELOC interest, savings interest or GIC/CD renewal, to the cent, and which central bank drives that product (Canada: Bank of Canada; US: the Federal Reserve). Use it when someone asks what a cut or a rise would mean for them. Pure arithmetic on the numbers they give; it never says whether a change will happen.

Input parameters:

- `balance` (number, required): Amount owed (mortgage, HELOC) or held (savings, GIC/CD), in dollars.
- `change_pts` (number, required): The change to work out, in percentage points: -0.25 for a quarter-point cut, 0.5 for a half-point rise.
- `compounding` (string): Mortgage only. Defaults to semi-annual in Canada, monthly in the US.
- `country` (string): Where the product is. Decides which central bank it follows and, for mortgages, the usual compounding. Ask if unsure.
- `months` (number): Mortgage: months left to pay it off (default 300). GIC/CD: the term in months (default 12).
- `product` (string, required): What to work out.
- `rate_pct` (number, required): The rate today, in percent a year.

Output parameters:

- `assumptions` (array)
- `country` (string)
- `follows` (string)
- `inputs` (object)
- `lines` (array)
- `notice` (string)
- `product` (string)
- `rows` (array)

### `decision_explainer` (~163 tokens)

A rate decision, explained from the statement

What the Federal Reserve, the Bank of Canada, the European Central Bank or the Bank of England decided at its latest rate decision (or the one before), how the official statement's wording changed from the previous one, word for word, and what the bank itself says it is watching, quoted with links. Use it when someone asks what a central bank just did or what changed. From the banks' own statements; it never says what the bank will do next.

Input parameters:

- `bank` (string, required): fed (Federal Reserve), boc (Bank of Canada), ecb (European Central Bank) or boe (Bank of England).
- `date` (string): Optional: the decision date, YYYY-MM-DD. Defaults to the latest; the one before is also kept.

Output parameters:

- `bank` (string)
- `changes` (array)
- `decision` (object)
- `institution` (string)
- `next` (object)
- `notice` (string)
- `previous` (object)
- `sources` (array)
- `watching` (array)

### `speech_tracker` (~135 tokens)

Central bankers' recent speeches

Recent speeches and remarks by Federal Reserve, Bank of Canada, ECB or Bank of England policymakers: who spoke, when, the title, the bank's own one-line description and a link to the full text. Use it when someone asks what central bankers have been saying. Descriptions are the bank's own words, attributed; nothing is added or interpreted.

Input parameters:

- `bank` (string, required): fed (Federal Reserve), boc (Bank of Canada), ecb (European Central Bank) or boe (Bank of England).
- `days` (number): How far back to look, in days (default 30, at most 90).

Output parameters:

- `bank` (string)
- `institution` (string)
- `notice` (string)
- `refreshedAt` (string)
- `speeches` (array)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp#diagnostics

## Score history

- 2026-11-21: 71
- 2026-11-20: 71
- 2026-11-19: 70
- 2026-11-18: 70
- 2026-11-17: 69
- 2026-11-16: 69

## Common questions

### What is the ATLAS Explain MCP server?

ATLAS Explain is an MCP server listed in the public MCP registry as io.github.MISHHF93/atlas-explain. Market jargon in plain language: terms, official figures, crypto prices and charts, headlines. This page covers its hosted endpoint (https://atlas-explain-mcp.atlas-explain.workers.dev/mcp).

### Is the ATLAS Explain MCP server safe to use?

ATLAS Explain scores 71 out of 100 on VerifyMCP. 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 ATLAS Explain MCP server expose?

ATLAS Explain exposes 21 tools: explain_term, browse_glossary, asset_details, official_figures, crypto_prices, and 16 more. Their descriptions and schemas cost roughly 2,968 tokens of context every time the server is loaded.

### Does the ATLAS Explain MCP server require authentication?

No. We connected to ATLAS Explain without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the ATLAS Explain MCP server still maintained?

ATLAS Explain is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the ATLAS Explain MCP server?

VerifyMCP ran 13 checks on ATLAS Explain, covering TLS certificate, Authorization, HSTS header, DNSSEC and 9 more. One item could not be completed, a gap on our side rather than a finding about ATLAS Explain: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://atlas-explain-mcp.atlas-explain.workers.dev/mcp
- Repository: https://github.com/MISHHF93/atlas-explain
- Website: https://atlas-explain.web.app/connect
- Changelog RSS feed: https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp.json
- HTML version of this page: https://verifymcp.io/servers/mishhf93-atlas-explain/atlas-explain-mcp
