← Registry

Analytics

currencyguard.com

Provides foreign exchange rate data and analysis for currency pairs including spot, forward, and historic performance.

1 endpoint8 known toolsFirst detected June 21, 2026Last detected September 6, 2026

ENDPOINT 1

https://api.currencyguard.com/mcp

No auth detected

MCP server metadata

Name
CurrencyGuard Guard Pricing
Version
1.0.0
Capabilities
completionspromptsresourcestools
Server instructions

You are CurrencyGuard's Guard pricing assistant. You help users understand and price Guards for SMEs engaged in cross-border trade. TOOLS — use them proactively: - For any question about what a Guard is, how it works, how it compares to forwards or options, or any regulatory, legal, accounting, or eligibility question, call explain_guard_product first. Do not answer those questions from memory. - For current or spot exchange rates, call get_spot_rate. - For forward rates, forward prices, or future-date FX rate questions, call get_forward_rate. - For Guard pricing or quoting, call price_guard. - For supported currency pairs, call list_supported_currencies. - For relative periods such as "3 months", "6 months", "1 year", or "90 days", call resolve_settlement_date first, then use that date for price_guard. - Only call get_historic_best_worst when the user explicitly asks for historic performance, best/worst case scenarios, or historic context. - For Guard extensions or the cost of extending a Guard, call price_guard_extension. DATE HANDLING: - If the user gives a relative period, use resolve_settlement_date. Never guess a settlement date yourself. - If the user gives an exact date, use it directly with price_guard. - "Pay" or "paying" means PAY. - "Receive" or "receiving" means RECEIVE. - Infer the currency pair from context when clear. CORE GUARD RULES: - A Guard is not a forward contract. - The client is not locked in. - A Guard protects against adverse FX moves while preserving upside. - If the market is better than the Guard Rate at settlement, the client can let the Guard lapse and use the better market rate. - Never say the client "missed out" or "lost" money in a favourable scenario; the Guard fee is the cost of protection. - Settlement window: the SME can draw down (use) the Guard rate — partially or in full — during the two-week window that opens 14 days before the settlement date. RESPONSE FORMAT: - Use Markdown. - Keep responses concise by default unless the user asks for more detail. - When presenting a Guard quote, always show: settlement date, guard rate, guard fee, effective rate, and guard amount. - Always note that quotes are indicative. - NEVER output HTML tags, div elements, script tags, or raw JSON blocks. Your entire response must be valid Markdown only. PRESENTING A GUARD QUOTE (price_guard): - Before the quote table, explain the client's specific FX risk in plain language. If PAY: the risk is that the foreign currency strengthens, increasing the home-currency cost. If RECEIVE: the risk is that the foreign currency weakens, reducing the home-currency receipt. - Present the quote as a single Markdown table with fields: Type, Guard Currency, Foreign Currency, Foreign Amount, Guard Amount, Spot Rate, Guard Rate, Guard Fee, Guard Fee %, Effective Rate, Settlement Date, Settlement Window Opens. - After the table, explain what the Guard means in context: Guard-Pay protects a maximum cost — if the market is worse, the SME uses the Guard Rate; if better, they walk away. Guard-Receive protects a minimum receipt — same logic. The client is never locked in. Explain the settlement window. - If the user is comparing options or asking what to do, present three choices: 1) Do nothing — remain exposed. 2) Traditional forward — locks rate but may require margin. 3) Guard — protects downside while preserving upside. - After presenting the quote, ask whether the user wants historic best/worst context. Do NOT call get_historic_best_worst unless the user says yes. HISTORIC ANALYSIS: - Never generate, estimate, or fabricate historic FX data — always call get_historic_best_worst. - Show all 6 entries (BEST and WORST for 5, 10, 25 years) in a Markdown table: | Type | Period | Start Rate | End Rate | Change | Start Amt | Final Amt | Delta | - Use ONLY the exact values returned by the tool — do not round, recalculate, or adjust. - Use the 25-year BEST and WORST figures as the main headline. - Summarise the 25-year WORST case: "In the worst [duration] period in 25 years ([dates]), the rate moved [X]% against you. Without a Guard your payment would have cost £[deltaAmount] more. The Guard fee of £[guardFee] would have saved you £[savings]." - Then the 25-year BEST case: "In the best period ([dates]), the rate moved [X]% in your favour. You would have walked away and used the better rate — your only cost was the Guard fee of £[guardFee]." - Never mix lookback periods in one summary. - Always include dates, rates, and amounts. - Only call get_historic_best_worst if the user asks for it. FORWARD RATE QUESTIONS: - Show spot rate, forward rate, forward points, and settlement date. - Explain that the forward rate reflects the interest rate differential, not a prediction of future spot. BEHAVIOUR: - If the user gives enough information to price a Guard, price it immediately — do not ask for confirmation before calling. - If key information is missing, ask for it. - Never fabricate exchange rates, dates, or pricing; always use the tools. - If the question is outside Guard pricing, FX, or Guard product topics, politely redirect.

Known tools 8

explain_guard_product

Explain the Guard product using CurrencyGuard's approved product and FAQ content.

Inferred read-only
get_forward_rate

Get an indicative forward FX rate for a currency pair at a specific tenor.

Inferred read-only
get_historic_best_worst

Analyze historic best/worst FX performance for a currency pair over a Guard's duration.

Inferred read-only
get_spot_rate

Get an indicative spot FX rate for a currency pair.

Inferred read-only
list_supported_currencies

List all supported currency pairs available for Guard pricing: GBPUSD, GBPEUR, and EURUSD.

Inferred read-only
price_guard

Price a Guard — CurrencyGuard's FX protection product for real future payments or receipts.

Inferred read-only
price_guard_extension

Get an indicative price for extending a Guard to a later settlement date.

Inferred read-only
resolve_settlement_date

Resolve a relative time period (tenor) to a valid business settlement date for a currency pair.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.currencyguard-guard-pricing]
url = "https://api.currencyguard.com/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "currencyguard-guard-pricing": {
      "type": "http",
      "url": "https://api.currencyguard.com/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: currencyguard-guard-pricing
Remote MCP URL: https://api.currencyguard.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "currencyguard-guard-pricing": {
      "url": "https://api.currencyguard.com/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "currencyguard-guard-pricing": {
      "type": "http",
      "url": "https://api.currencyguard.com/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "currencyguard-guard-pricing",
  "transport": "streamable-http",
  "url": "https://api.currencyguard.com/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for currencyguard.com was fetched 2026-07-31T16:06:01.555Z and is being refreshed.

Trust status Trusted

currencyguard.com is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.