euroref — European government reference data

get_changes

Read-onlyIdempotent

FREE unmetered change + freshness feed. After any paid series or answer call, call this before you assume the cached value is still the law. Returns every series whose current value took effect on or after since (default last 30 days), newest first, each with last_confirmed and stale, PLUS a dataset-wide freshness summary: how many of the served series were re-verified within 1/7/30/90 days, how many are past their window, and which single series has gone longest without a check. Freshness is checkable or it is marketing. Args: since? (YYYY-MM-DD). Do not re-pay get_series to discover a diff. For a push bind, use register_alert (Register: $0 · Delivery after trial: $0.05). For a filing freeze of the current value, GET /v1/certified/{country}/{series} ($0.10).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`since`	No	YYYY-MM-DD. Omit for the server default (last 30 days). Free, unmetered.

Output Schema

TableJSON Schema

Name	Required	Description
`as_of`	No
`error`	No	Present on a free refusal or error; no charge
`since`	No
`changes`	No
`no_charge`	No
`price_usd`	No
`disclaimer`	No
`how_to_pay`	No
`bind_series`	No
`explanation`	No
`x_next_bind`	No
`http_endpoint`	No
`payment_required`	No	true when the call needs payment; how_to_pay explains x402 or card

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "Value changes since a date",
+  "properties": {
+    "as_of": {},
+    "bind_series": {},
+    "changes": {
+      "items": {},
+      "type": "array"
+    },
+    "disclaimer": {},
+    "error": {
+      "description": "Present on a free refusal or error; no charge"
+    },
+    "explanation": {},
+    "how_to_pay": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "http_endpoint": {
+      "type": "string"
+    },
+    "no_charge": {
+      "type": "boolean"
+    },
+    "payment_required": {
+      "description": "true when the call needs payment; how_to_pay explains x402 or card",
+      "type": "boolean"
+    },
+    "price_usd": {
+      "type": "number"
+    },
+    "since": {},
+    "x_next_bind": {}
+  },
+  "type": "object"
+}

AddedSep 25, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover read-only, idempotent, open-world, and non-destructive traits, and the description still adds substantial behavioral context beyond them: return ordering (newest first), per-row fields (last_confirmed, stale), the 1/7/30/90-day freshness buckets, and pricing/metering ($0 free, alternatives at $0.05/$0.10). Nothing is left for the agent to infer about cost or shape.

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?

Front-loaded with the key fact ('FREE unmetered') and well organized, but it carries some non-essential weight: the slogan 'Freshness is checkable or it is marketing' does no routing work, and pricing parentheticals add length. Still, most sentences earn their place by steering the agent away from paid alternatives.

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

Completeness5/5

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

An output schema exists, so return values needn't be fully enumerated, yet the description still describes the shape (per-series freshness fields plus a dataset summary). Combined with the alternatives and cost model, an agent has everything needed to select and invoke this correctly.

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% for the single `since` parameter, so the baseline is 3, but the description adds genuine semantic meaning beyond the schema's format note: it defines what `since` filters on (series whose current value *took effect* on or after that date) and restates the default window. The added value is real, though modest for a one-param tool.

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?

States a specific verb+resource combination ('FREE unmetered change + freshness feed') and precisely what it returns: every series whose current value took effect on or after `since`, plus a dataset-wide freshness summary. It differentiates itself from siblings by naming get_series, register_alert, and the certified endpoint as distinct things to use instead.

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

Usage Guidelines5/5

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

Explicit trigger ('After any paid series or answer call, call this before you assume the cached value is still the law'), an explicit anti-pattern ('Do not re-pay get_series to discover a diff'), and named alternatives with conditions ('For a push bind, use register_alert', 'For a filing freeze ... GET /v1/certified/...'). When/when-not/alternatives are all covered.

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

All euroref — European government reference data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?