What can you do with this server?

This server provides real-time and historical foreign-exchange data to AI assistants via the Model Context Protocol. * Get current exchange rate (get_exchange_rate): Fetch the live mid-market rate between any two of 150+ currencies using ISO 4217 codes (e.g., USD → EUR). Rates refresh every ~60 seconds from tier-1 sources. * Get historical rates (get_historical_rates): Retrieve time-series data for a currency pair over fixed periods: * 1d — hourly data (24 points) * 7d — daily data (7 points) * 30d — daily data (30 points) * 1y — weekly data (52 points) * Multi-currency lookups (get_rates_authenticated): Fetch rates from one source currency to multiple targets in a single call (e.g., USD → EUR, GBP, JPY), with optional historical timestamps and grouping by hour, day, week, or month. * List supported currencies (list_currencies): Retrieve all 150+ available currencies with their ISO code, full name, and symbol. Results are cached for 24 hours. Most features require an AllRatesToday API key. Clear error messages are provided for missing keys, quota limits, and invalid requests.

de en es ja ko ru zh

AllRatesToday MCP Server

by AllRates-Today

Overview Schema Related Servers Score Discussions

TypeScript

Remote

AllRatesToday MCP Server — @allratestoday/mcp-server

npm version npm downloads license MCP TypeScript

English | 简体中文

Give your AI assistant a live window into the foreign-exchange market. A Model Context Protocol server that lets Claude Code, Cursor, Claude Desktop, Windsurf, and any MCP-compatible client fetch real-time currency rates, historical series, and multi-currency lookups from the AllRatesToday API.

After installation, your assistant can answer questions like:

"What's the current USD to EUR rate?"
"Show me how GBP/JPY moved over the last 30 days."
"Convert 250 USD into CAD at a real rate."
"Compare USD against EUR, GBP, and JPY simultaneously."

🚀 Why this server?

📡 Live mid-market rates — 150+ ISO 4217 currencies, refreshed every ~60 seconds from institutional interbank data
📈 Historical series built in — 1d / 7d / 30d / 1y windows with sensible granularity per period
🧰 Four focused tools — get_exchange_rate, get_historical_rates, get_rates_authenticated, list_currencies; small surface, easy for the model to use correctly
🔌 Works everywhere MCP does — stdio transport, MCP 1.x; Claude Code, Cursor, Claude Desktop, Windsurf, or any generic host
🔓 Works with no API key — installs and answers out of the box from the open ECB reference table; a free key unlocks real-time rates for 160+ currencies
🛡️ Honest about what it returned — every keyless answer says which rate it is and when it was published; API errors map to clear, actionable messages
🔒 Nothing leaks — only the request parameters and your API key ever reach allratestoday.com; never conversation context

Related MCP server: currency-exchange-mcp

⚖️ Mid-market vs official central-bank rates

Everything this server returns is a mid-market rate: the live interbank midpoint, refreshed every ~60 seconds — the right number for price display, conversion, and anything that should track the market. It is not the official rate a tax authority or auditor may require. For those, AllRatesToday also serves published central-bank and tax-authority rates (100+ sources — ECB, Fed, HMRC, US Treasury, …) that are fixed once published and carry the institution's own publication date — via the central bank REST API and per-bank npm SDKs. The two can diverge by several percent, so pick by use case, not convenience.

🔓 Keyless mode — what works with no setup

Install it with no configuration at all and it starts, connects, and answers:

Tool	Keyless	What you get
`get_exchange_rate`	✅	Official ECB daily reference rate, ~30 major currencies. The response carries `rate_date` and a note saying so, so the assistant never passes it off as a live quote.
`list_currencies`	✅	All 160+ supported ISO 4217 codes.
`get_historical_rates`	🔑	Returns one sentence explaining how to get a free key.
`get_rates_authenticated`	🔑	Same.

The keyless path reads the open, edge-cached /api/open/central-bank/ecb endpoint — no upstream cost, no rate limit to trip over, nothing to sign up for.

🔑 Get your API key (free)

A key unlocks real-time mid-market rates across 160+ currencies, historical series, and multi-target / point-in-time lookups. The free tier is enough for development and personal use — no credit card required.

Register at allratestoday.com/register — 30 seconds
Verify your email
Copy your key from the dashboard (format: art_live_xxxxx)
Use it as ALLRATES_API_KEY in the configs below

Without one the server prints a short summary of keyless mode on stderr and keeps running — it never exits, because an MCP server that exits breaks the host client's whole configuration.

🧩 Easiest install: the Claude Code plugin

If you use Claude Code, install the plugin instead of configuring this server by hand — it bundles both AllRatesToday MCP servers, two skills, and five slash commands (/rate, /convert, /official-rate, /fx-history, /add-currency-support):

/plugin marketplace add AllRates-Today/claude-code-plugin
/plugin install allratestoday@allratestoday

Everything below still applies for other MCP clients.

📦 Installation

The simplest install is zero-install via npx, which is what every config below uses:

# Run without installing (recommended)
npx -y @allratestoday/mcp-server

# Or install globally
npm install -g @allratestoday/mcp-server
allratestoday-mcp

Both commands launch the stdio MCP server and wait for a client to connect — they're not meant to be run interactively from your shell; your MCP client launches them as a subprocess.

🏁 Quick setup per client

Each client reads MCP servers from a different config file. Pick yours below.

Claude Code

The fastest path uses the built-in CLI:

claude mcp add allratestoday -- npx -y @allratestoday/mcp-server
claude mcp env allratestoday ALLRATES_API_KEY=art_live_xxxxx

Restart Claude Code. Verify by asking it: "What's the current USD to EUR rate?"

Cursor

Edit ~/.cursor/mcp.json (or .cursor/mcp.json inside your project for project-scoped servers):

{
  "mcpServers": {
    "allratestoday": {
      "command": "npx",
      "args": ["-y", "@allratestoday/mcp-server"],
      "env": {
        "ALLRATES_API_KEY": "art_live_xxxxx"
      }
    }
  }
}

Restart Cursor. The four tools should appear in the MCP tool picker.

Claude Desktop

Edit the config file (path depends on OS):

OS	Path
macOS	`~/Library/Application Support/Claude/claude_desktop_config.json`
Windows	`%APPDATA%\Claude\claude_desktop_config.json`
Linux	`~/.config/Claude/claude_desktop_config.json`

{
  "mcpServers": {
    "allratestoday": {
      "command": "npx",
      "args": ["-y", "@allratestoday/mcp-server"],
      "env": {
        "ALLRATES_API_KEY": "art_live_xxxxx"
      }
    }
  }
}

Fully quit and reopen Claude Desktop (Cmd+Q on macOS, right-click tray icon → Exit on Windows). Closing the window alone keeps the old config loaded.

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json with the same mcpServers block as above, then restart Windsurf.

Generic stdio MCP client

Any MCP host that supports stdio transport works. The launch command is:

npx -y @allratestoday/mcp-server

…with the environment variable ALLRATES_API_KEY set. The protocol version is MCP 1.x.

✅ Verify it works

After configuring your client, test in this order:

Server starts — open the client. A red dot or "failed to connect" means the API key is missing or wrong (see Troubleshooting below).
Tools are listed — most clients have a "tools" or "MCP" panel showing the four tools.
A live call returns a number — ask: "What's the current USD to EUR rate?" The assistant should call get_exchange_rate(source: "USD", target: "EUR") and reply with a real rate. If it fabricates a number without a tool call, the server isn't connected.

📚 Tools reference

get_exchange_rate — current rate for one pair
get_historical_rates — time series over a preset period
get_rates_authenticated — multiple targets in one call, optional point-in-time
list_currencies — all supported currency codes, names, symbols

All four tools require ALLRATES_API_KEY.

`get_exchange_rate`

Current mid-market rate between two currencies.

Input

Field	Type	Required	Description
`source`	string	yes	3-letter ISO 4217 code, e.g. `USD`
`target`	string	yes	3-letter ISO 4217 code, e.g. `EUR`

Example call

{ "source": "USD", "target": "EUR" }

Response:

{ "rate": 0.92145, "source": "wise" }

`get_historical_rates`

Time-series data points for a currency pair over a fixed period.

Input

Field	Type	Required	Description
`source`	string	yes	Source currency code
`target`	string	yes	Target currency code
`period`	string	no (default `7d`)	One of `1d`, `7d`, `30d`, `1y`

Granularity by period

`period`	Data points
`1d`	Hourly (24 points)
`7d`	Daily (7 points)
`30d`	Daily (30 points)
`1y`	Weekly (52 points)

Example call

{ "source": "USD", "target": "INR", "period": "30d" }

Response (truncated):

{
  "source": "USD",
  "target": "INR",
  "period": "30d",
  "data": [
    { "date": "2026-03-27T00:00:00Z", "rate": 83.42, "timestamp": 1743033600000 },
    { "date": "2026-03-28T00:00:00Z", "rate": 83.51, "timestamp": 1743120000000 },
    "..."
  ]
}

`get_rates_authenticated`

Multiple targets in one call, with optional historical timestamp or grouping window.

Input

Field	Type	Required	Description
`source`	string	yes	Source currency code
`target`	string	yes	One or more codes, comma-separated (`EUR,GBP,JPY`)
`time`	string (ISO 8601)	no	Historical point in time
`group`	string	no	One of `hour`, `day`, `week`, `month`

Example call

{ "source": "USD", "target": "EUR,GBP,JPY" }

Response:

[
  { "rate": 0.9214, "source": "USD", "target": "EUR", "time": "2026-04-26T11:00:00Z" },
  { "rate": 0.7891, "source": "USD", "target": "GBP", "time": "2026-04-26T11:00:00Z" },
  { "rate": 151.34, "source": "USD", "target": "JPY", "time": "2026-04-26T11:00:00Z" }
]

`list_currencies`

All supported currencies with codes, names, and symbols. Cached upstream for 24 hours — cheap to call for validating user input before the other tools.

Input — none.

Response (truncated):

{
  "currencies": [
    { "code": "USD", "name": "US Dollar", "symbol": "$" },
    { "code": "EUR", "name": "Euro", "symbol": "€" },
    { "code": "GBP", "name": "British Pound", "symbol": "£" },
    "..."
  ],
  "count": 162
}

⚙️ Environment variables

Variable	Default	Required	Purpose
`ALLRATES_API_KEY`	—	no	Your API key. Unset ⇒ keyless mode (see above); set ⇒ real-time rates and the historical tools.
`ALLRATES_BASE_URL`	`https://allratestoday.com/api`	no	Override for self-hosted or staging deployments.

Set these in your MCP client's config (in the env block) — not in your shell — because MCP servers are launched as subprocesses with isolated environments.

💳 Plans

A free tier and paid plans are available — see allratestoday.com/pricing for current quotas. All plans include the same currency coverage and historical depth; only the request quotas differ.

🛠️ Troubleshooting

Symptom	Likely cause	Fix
Client shows "MCP server failed to start" or red dot	Not a missing key — 0.5.0+ starts fine without one. Usually `npx` cannot reach the registry, or Node is older than 18	Run `npx -y @allratestoday/mcp-server` in a shell and read stderr
Rates look like yesterday's, response mentions "keyless mode"	No key set, so answers come from the ECB daily reference table	Set `ALLRATES_API_KEY` for real-time mid-market rates
Every call returns "Invalid AllRatesToday API key"	Key is malformed (missing prefix, truncated, or revoked)	Copy a fresh key from the dashboard
Tools return "AllRatesToday API quota exceeded"	Monthly limit hit	Wait until next month or upgrade plan
Historical tool returns "Bad request"	Invalid period or unknown currency code	Period must be `1d`/`7d`/`30d`/`1y`; codes must be 3 letters
Server starts but tools never appear	Client didn't reload after config change	Fully quit (not just close) and reopen the client
`npx` runs but hangs forever	The server is waiting for an MCP client to connect — normal when run from a shell	Let your MCP client launch it

To inspect what the server is doing, run it manually with the key set:

ALLRATES_API_KEY=art_live_xxxxx npx -y @allratestoday/mcp-server

No output means healthy (stdio is reserved for the MCP protocol); errors print to stderr.

🛡️ Error reference

The server maps API errors to clear, actionable messages the assistant can relay to the user:

HTTP status	Meaning	Tool error message
200	Success	(rate returned)
400	Bad request — usually unknown currency code	`Bad request — possibly an unknown currency code`
401	Invalid or missing API key	`Invalid AllRatesToday API key`
429	Quota exceeded	`AllRatesToday API quota exceeded`
5xx	Server-side issue at allratestoday.com	`HTTP 5xx — <upstream message>`

❓ FAQ

Is the free plan really enough for normal use? Yes for personal/dev use. Heavy interactive use, multiple chat sessions per day, or production should consider the paid tiers.

Do you store my conversation or query data? No. Only your API key and the request parameters (source, target, period, time) are sent to allratestoday.com — never the LLM's conversation context.

What happens to my API key? It's only sent as a Bearer token in the Authorization header on requests to the AllRatesToday API. It's never logged or transmitted elsewhere.

Why is my first call slow? Cold-start of npx (first run downloads the package) plus the initial cache miss. Subsequent calls are typically <200ms.

Can I run this without npm/Node? Not currently — Node ≥18 is required. If a standalone binary matters to you, open an issue.

Is there a self-hosted option? Set ALLRATES_BASE_URL to your own AllRatesToday instance. Contact support@allratestoday.com for self-hosted licensing.

Does this work with ChatGPT? MCP works with any MCP-compatible client. ChatGPT Desktop has experimental MCP support; check OpenAI's docs for current status.

👩‍💻 Development

git clone https://github.com/cahthuranag/mcp-server.git
cd mcp-server
npm install
npm run build
ALLRATES_API_KEY=art_live_xxxxx node dist/index.js

The server runs on stdio and waits for an MCP client to connect; Ctrl+C to exit. npm run dev watches and rebuilds. To test against a local AllRatesToday instance:

ALLRATES_BASE_URL=http://localhost:8080/api ALLRATES_API_KEY=test_key node dist/index.js

Project structure

src/
├── index.ts      # MCP server, tool registration, request handlers
└── client.ts     # HTTP client for AllRatesToday API + error mapping
dist/             # Compiled JS (gitignored)
server.json       # MCP registry manifest

Contributing — issues and PRs welcome at github.com/cahthuranag/mcp-server. Before opening a PR: npm run build must succeed, test against a real API key, and update the tool descriptions in src/index.ts plus this README's tools reference if you change tool behavior.

📝 Changelog

See GitHub Releases for the full list. Recent highlights:

0.5.0 — Keyless mode: the server starts and answers without an API key (get_exchange_rate via the open ECB reference table, list_currencies unchanged); metered tools return actionable sign-up guidance instead of the process exiting
0.4.x — README overhaul; registry metadata updates
0.3.x — API key required for all tools; fail-fast at startup with clear error
0.2.x — Removed news tool, required auth on get_historical_rates
0.1.x — Initial release with 5 tools

🔗 Links

API documentation · Interactive reference
Register (free) · Pricing
MCP protocol docs
GitHub · Bug reports
Support: support@allratestoday.com

📜 License

MIT — see LICENSE.

Available Tools

4 tools

get_exchange_rateA

Get the current mid-market exchange rate between two currencies. Returns a single rate number. No API key required.

ParametersJSON Schema

Name	Required	Description	Default
`source`	Yes	ISO 4217 currency code (e.g. USD, EUR, GBP).
`target`	Yes	ISO 4217 currency code (e.g. USD, EUR, GBP).

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations provided, the description carries full burden. It discloses key behavioral traits: returns a 'single rate number' (output format), 'No API key required' (authentication needs), and 'current mid-market' (rate type). It doesn't mention rate limits, error conditions, or data freshness, but provides useful operational context.

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

Conciseness5/5

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

Three concise sentences that each earn their place: states purpose, specifies return format, and discloses authentication requirement. No wasted words, front-loaded with core functionality.

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?

For a simple 2-parameter read operation with no output schema, the description provides good coverage: purpose, return format, and authentication context. It could mention data source or refresh frequency for completeness, but covers the essentials well given the tool's simplicity.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema (both parameters are ISO 4217 codes). Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose5/5

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

The description clearly states the verb ('Get'), resource ('current mid-market exchange rate'), and scope ('between two currencies'). It distinguishes from sibling tools by specifying it returns a 'single rate number' (vs. historical rates or authenticated rates) and 'No API key required' (vs. get_rates_authenticated).

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool ('Get the current mid-market exchange rate') and implicitly contrasts with siblings through 'No API key required' (vs. get_rates_authenticated) and 'single rate number' (vs. historical data). However, it doesn't explicitly state when NOT to use this tool or name alternatives directly.

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

get_historical_ratesB

Get historical exchange-rate data points for a currency pair over a period. Periods: 1d (hourly), 7d (daily), 30d (daily), 1y (weekly). Requires an AllRatesToday API key (ALLRATES_API_KEY).

ParametersJSON Schema

Name	Required	Description	Default
`source`	Yes	ISO 4217 currency code (e.g. USD, EUR, GBP).
`target`	Yes	ISO 4217 currency code (e.g. USD, EUR, GBP).
`period`	No	Time period to fetch history for.	7d

TDQS

B3.4/5.0

Behavior3/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It adds useful context: it specifies the API key requirement (ALLRATES_API_KEY) and describes the data granularity for each period (e.g., hourly for 1d, daily for 7d/30d, weekly for 1y), which goes beyond the input schema. However, it does not cover other behavioral aspects such as rate limits, error handling, response format, or whether it's a read-only operation, leaving gaps for a tool with authentication needs.

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

Conciseness4/5

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

The description is appropriately sized with two sentences: the first states the purpose and period details, and the second specifies the API key requirement. It is front-loaded with key information and avoids unnecessary words, though it could be slightly more structured (e.g., separating period details into a list). Every sentence adds value, making it efficient but not perfectly optimized.

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

Completeness3/5

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

Given the tool's complexity (3 parameters, authentication requirement, no output schema), the description is moderately complete. It covers the purpose, period options with granularity, and authentication need, but lacks details on output format, error cases, or sibling tool differentiation. Without annotations or an output schema, more behavioral context would be beneficial, but it meets a minimum viable level for basic understanding.

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

Parameters3/5

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

The input schema has 100% description coverage, with clear documentation for source, target, and period parameters. The description adds minimal value beyond the schema: it mentions 'currency pair' which aligns with source/target, and lists the period options with data granularity details, but does not provide additional syntax, format, or usage examples. Given the high schema coverage, a baseline score of 3 is appropriate as the description compensates slightly but not significantly.

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 clearly states the tool's purpose: 'Get historical exchange-rate data points for a currency pair over a period.' It specifies the verb ('Get'), resource ('historical exchange-rate data points'), and scope ('currency pair over a period'), which distinguishes it from siblings like get_exchange_rate (likely current rates) and list_currencies (likely currency metadata). However, it doesn't explicitly differentiate from get_rates_authenticated, which might also provide historical data, leaving some ambiguity.

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?

The description provides implied usage context by listing available periods (1d, 7d, 30d, 1y) and stating it requires an AllRatesToday API key, which suggests when to use it (for historical data with specific timeframes and authentication). However, it lacks explicit guidance on when to use this tool versus alternatives like get_rates_authenticated or get_exchange_rate, and does not mention any exclusions or prerequisites beyond the API key.

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

get_rates_authenticatedA

Get rates with higher limits and multi-target support. Requires an AllRatesToday API key (ALLRATES_API_KEY). Supports comma-separated targets like "EUR,GBP,JPY".

ParametersJSON Schema

Name	Required	Description
`source`	Yes	ISO 4217 currency code (e.g. USD, EUR, GBP).
`target`	Yes	One or more target codes, comma-separated.
`time`	No	Optional historical ISO 8601 timestamp.
`group`	No	Optional grouping window.

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds useful context: authentication requirements (AllRatesToday API key), rate limit characteristics ('higher limits'), and input format for targets ('comma-separated'). However, it doesn't describe the return format, error conditions, or what 'higher limits' specifically means compared to other tools.

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

Conciseness5/5

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

The description is extremely concise and front-loaded with the most important information. Every sentence earns its place: the first states the core purpose and key differentiators, the second covers authentication requirements, and the third provides a concrete example of parameter usage. No wasted words.

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

Completeness3/5

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

Given no annotations and no output schema, the description provides adequate but incomplete context. It covers authentication, rate limits, and multi-target format, but doesn't describe the return values, error handling, or how it differs from sibling tools beyond 'higher limits.' For a tool with 4 parameters and authentication requirements, more behavioral context would be helpful.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema: it clarifies the 'target' parameter accepts 'comma-separated targets like EUR,GBP,JPY' which is implied but not explicitly stated in the schema description. This meets the baseline of 3 when schema coverage is high.

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 clearly states the tool's purpose: 'Get rates with higher limits and multi-target support.' It specifies the action ('Get rates') and key capabilities (higher limits, multi-target support). However, it doesn't explicitly differentiate from sibling tools like 'get_exchange_rate' or 'get_historical_rates' beyond mentioning higher limits and multi-target support.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool: when higher limits and multi-target support are needed, and when an AllRatesToday API key is available. It mentions 'comma-separated targets' as a specific usage pattern. However, it doesn't explicitly state when NOT to use it or name alternatives among the sibling tools.

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

list_currenciesA

List all supported currencies with code, name, and symbol. No API key required. Cached 24h upstream.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively adds context beyond the input schema by specifying that no API key is needed (implying no authentication requirements) and that data is cached for 24 hours upstream (indicating potential rate limits or freshness considerations). However, it does not detail response format or error handling.

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

Conciseness5/5

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

The description is highly concise and front-loaded, consisting of two sentences that efficiently convey the tool's purpose, key features (no API key, caching), and scope. Every sentence adds value without redundancy, making it easy to parse quickly.

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?

Given the tool's low complexity (0 parameters, no output schema, no annotations), the description is largely complete, covering purpose, authentication, and caching. However, without an output schema, it could benefit from briefly mentioning the return format (e.g., list of objects with code, name, symbol) to fully guide usage.

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?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately does not discuss parameters, maintaining focus on the tool's purpose and behavior, which aligns with the baseline expectation for tools with no parameters.

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

Purpose5/5

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

The description clearly states the specific action ('List all supported currencies') and resource ('currencies'), with explicit details on what information is included ('code, name, and symbol'). It effectively distinguishes from sibling tools like get_exchange_rate or get_historical_rates, which focus on rates rather than listing currencies.

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

Usage Guidelines4/5

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

The description provides clear context by stating 'No API key required' and 'Cached 24h upstream', which helps determine when to use this tool (e.g., for basic currency info without authentication). However, it does not explicitly mention when not to use it or name alternatives among siblings, such as get_rates_authenticated for authenticated rate data.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.2.0Apr 21, 2026
- First observedget_exchange_rate
- First observedget_historical_rates
- First observedget_rates_authenticated
- First observedlist_currencies

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.8/5.0

Disambiguation3/5

The tools have some overlap in purpose, particularly between get_exchange_rate and get_rates_authenticated, which both retrieve current exchange rates but with different features (single vs. multi-target). However, the descriptions clarify the distinctions, and the other tools (get_historical_rates, list_currencies) are clearly distinct. This creates a moderate level of ambiguity that agents can navigate with careful reading.

Naming Consistency4/5

The tool names follow a consistent verb_noun pattern (e.g., get_exchange_rate, get_historical_rates, list_currencies), with all using snake_case. The only minor deviation is get_rates_authenticated, which uses 'authenticated' as an adjective rather than a noun, but it still fits the overall style. This consistency makes the tools predictable and easy to understand.

Tool Count5/5

With 4 tools, this server is well-scoped for its purpose of providing exchange rate data. Each tool serves a distinct function (current rates, historical rates, authenticated rates, currency listing), and there are no redundant or trivial additions. This count is appropriate for the domain, allowing comprehensive coverage without overwhelming complexity.

Completeness4/5

The tool surface covers the core needs for exchange rate data: retrieving current rates (with both basic and authenticated options), accessing historical data, and listing supported currencies. A minor gap is the lack of tools for currency conversion calculations or advanced analytics, but agents can work around this by combining the provided rates. Overall, it supports key workflows without dead ends.

Maintenance

ActivityActive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

fx-rates
io.github.HyosikPark
Live and historical FX rates (ECB via Frankfurter) — paid per call (x402/credits), 2 tools
Finance Open Data
1
FX Converter MCP A
io.github.Lulu-The-Narwhal
Free, keyless real-time currency conversion and exchange rates for any currency pair.
Finance Open Data
21
exchangerate.dev A
dev.exchangerate
Free, source-labeled FX rates: 465 pairs across 31 currencies, majors update ~60s intraday.
Finance Open Data
62
exchange-rates-mcp-server A
io.github.cyanheads
Convert currencies, get FX rates, and query historical ECB exchange rate data.
Finance Open Data
721

Related MCP Servers

FX Currency MCP Server
Finance Search Open Data
pavm035
F
license
Not graded
quality
D
maintenance
Provides real-time and historical foreign exchange rates for 31+ currencies, enabling currency conversion, historical rate lookups, and time series analysis using data from the Frankfurter API.
Updated 8 months ago (2025-12-24 23:41 UTC)
-
currency-exchange-mcp
Ruddxxy
A
license
Not graded
quality
D
maintenance
Real-time currency exchange rates and crypto prices via MCP. Convert between 60+ fiat currencies and 30+ cryptocurrencies with multi-source failover. No API keys needed for upstream data.
Updated 7 months ago (2026-02-16 08:08 UTC)
21
ISC
Realtime Exchange Rate MCP
Finance
AllRates-Today
A
license
A
quality
B
maintenance
Provides real-time foreign-exchange rates, historical data, and multi-currency lookups to MCP-compatible AI coding assistants like Claude Code and Cursor.
Updated 5 days ago (2026-08-31 20:36 UTC)
4
127
MIT
xe-mcp
Finance Data Visualization
CedricConday
A
license
A
quality
B
maintenance
An MCP server for the Xe Currency Data API that brings live FX rates, historical analysis, and quant-flavored tools into AI tools, working out of the box with zero credentials via Frankfurter/ECB data.
Updated 2 months ago (2026-07-06 15:46 UTC)
12
14
1
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AllRates-Today/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server