Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
FX Reference Rates is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
96/100
tool-list score
9
tools declared
remote
at its publisher
—
calls last 7d
What it does
ECB FX rates, cloud GPU and LLM API prices, World Bank country macro data; pay per call via x402
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http fx-reference-rates-mcp https://fx-reference-rates.regnotes.workers.dev/mcp
# 2 — ask your agent for something these tools do
# rates_latest, convert, rates_historical and 6 more
FX Reference Rates costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
REAll 3 servers
regnotes3 servers
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http fx-reference-rates-mcp https://fx-reference-rates.regnotes.workers.dev/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Today's exchange rates (forex reference rates, most recent ECB publication) for ~30 currencies in any base currency, e.g. USD to JPY, CNY, EUR, GBP, HKD, SGD, KRW, INR. Filter with symbols. Returns as_of date and source attribution. Costs $0.001 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | no | Base currency (default EUR) |
| symbols | string | no | Comma-separated currencies (default all) |
Currency converter: convert an amount between any two of ~30 currencies (e.g. 100 USD to JPY) at the latest ECB reference rate or as of a past date. Returns rate, result and as_of date. Costs $0.001 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| from | string | yes | ISO 4217 |
| to | string | yes | ISO 4217 |
| amount | number | yes | Number |
| date | string | no | Optional YYYY-MM-DD |
ECB reference rates on a given date in any base; non-publication days fall back to the previous publication day (as_of). Costs $0.002 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| date | string | yes | YYYY-MM-DD |
| base | string | no | Base currency (default EUR) |
| symbols | string | no | Comma-separated currencies |
Daily reference rate series for base/symbol between start and end (max 366 days), with min/max/mean and change. Costs $0.003 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| base | string | yes | ISO 4217 |
| symbol | string | yes | ISO 4217 |
| start | string | yes | YYYY-MM-DD |
| end | string | yes | YYYY-MM-DD |
Cloud GPU price comparison: hourly list prices of GPU / AI accelerator instances (H100, H200, A100, L40S, L4, A10G, T4, B200, MI300X, Trainium, Inferentia ...) on AWS and Azure in US, EU and Asia regions, on-demand and Azure Spot, ranked by USD per GPU-hour. Filter by gpu model, cloud, region, pricing. Official provider price APIs, refreshed daily. Costs $0.005 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| gpu | string | no | GPU/accelerator model or instance substring, e.g. H100, A100, L4, trainium |
| cloud | string | no | aws or azure |
| region | string | no | e.g. us-east-1, eastus, japaneast |
| pricing | string | no | on_demand or spot |
| limit | integer | no | 1-100, default 20 |
LLM API pricing lookup: USD per 1M input, output and cached-input tokens plus context window for ~3,300 models (OpenAI GPT, Anthropic Claude, Google Gemini, DeepSeek, Llama, Mistral, Qwen, xAI ...) across providers (direct, Azure, Bedrock, Vertex, Together, Fireworks ...). Filter by model and provider; sorted by input price. Costs $0.005 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| model | string | yes | Model name substring, e.g. gpt-5, claude-sonnet, gemini-2.5 |
| provider | string | no | Provider substring, e.g. openai, anthropic, bedrock |
| limit | integer | no | 1-100, default 25 |
Country economic profile: latest value and year plus annual history (2005 onward) for 21 World Bank World Development Indicators: GDP (USD), real GDP growth, GDP per capita, GNI per capita PPP, CPI inflation, unemployment, population, exports/imports % GDP, current account % GDP, central government debt % GDP, tax revenue % GDP, real and lending interest rates, FDI inflows % GDP, total reserves, o
| Parameter | Type | Required | Notes |
|---|---|---|---|
| country | string | yes | ISO 3166 alpha-3 or alpha-2 code or country name, e.g. JPN, US, Brazil |
| years | integer | no | history years to include, 0-25, default 10 |
Macroeconomic time series: one World Development Indicator (e.g. inflation_cpi_pct, gdp_growth_pct, central_govt_debt_pct_gdp) for up to 20 countries over a year range, annual values. See free /macro/indicators for keys. CC BY 4.0. Costs $0.01 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| indicator | string | yes | indicator key from /macro/indicators, e.g. inflation_cpi_pct |
| countries | string | yes | comma-separated ISO3/ISO2 codes, max 20 |
| start | integer | no | first year, default 2015 |
| end | integer | no | last year, default latest |
Country ranking: sort all economies by one World Development Indicator for a year (default: each country's latest value), highest first or lowest first, optionally filtered by World Bank region or income group. Aggregates (World, regions) excluded unless requested. CC BY 4.0. Costs $0.02 USDC on Base via x402.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| indicator | string | yes | indicator key from /macro/indicators |
| year | integer | no | year; default latest available per country |
| region | string | no | World Bank region substring, e.g. Latin America, Sub-Saharan |
| income | string | no | income group substring, e.g. High income, Lower middle |
| order | string | no | desc (default) or asc |
| limit | integer | no | 1-300, default 50 |
| aggregates | string | no | true to include regional/income aggregates |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install FX Reference Rates or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 96 / 100
Release 1.1.0 · scanned 28 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score96
Findings0 threat · 0 capability
Capabilityminimal
Coveragemanifest
Verificationnot in this report
Surface digest67f42d2ffdc378243043eec83b6697b0df091df0f73b8229cd38786231bda309
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| rates_latest | no tags | |
| convert | no tags | |
| rates_historical | no tags | |
| rates_timeseries | no tags | |
| ai_gpu_prices | no tags | |
| ai_llm_prices | no tags | |
| macro_country | no tags | |
| macro_indicator | no tags | |
| macro_rank | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest67f42d2ffdc37824
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.1.0.
1.1.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish FX Reference Rates can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.