@cyanheads/eurostat-mcp-server 0.6.5 → 0.8.0

package/AGENTS.md

@@ -1,7 +1,7 @@
 # Agent Protocol
 
 **Server:** @cyanheads/eurostat-mcp-server
-**Version:** 0.6.5
+**Version:** 0.8.0
 **Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.6`
 **Engines:** Bun ≥1.4.0, Node ≥24.0.0
 **MCP SDK:** `@modelcontextprotocol/server` `^2.0.0`

package/CLAUDE.md

@@ -1,7 +1,7 @@
 # Agent Protocol
 
 **Server:** @cyanheads/eurostat-mcp-server
-**Version:** 0.6.5
+**Version:** 0.8.0
 **Framework:** [@cyanheads/mcp-ts-core](https://www.npmjs.com/package/@cyanheads/mcp-ts-core) `^0.13.6`
 **Engines:** Bun ≥1.4.0, Node ≥24.0.0
 **MCP SDK:** `@modelcontextprotocol/server` `^2.0.0`

package/README.md

@@ -7,9 +7,7 @@
 
 <div align="center">
 
-
-
-[![Version](https://img.shields.io/badge/Version-0.6.5-blue.svg?style=flat-square)](./CHANGELOG.md) [![License](https://img.shields.io/badge/License-Apache%202.0-orange.svg?style=flat-square)](./LICENSE) [![Docker](https://img.shields.io/badge/Docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white)](https://github.com/users/cyanheads/packages/container/package/eurostat-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^2.0.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/eurostat-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/eurostat-mcp-server) [![TypeScript](https://img.shields.io/badge/TypeScript-^7.0.2-3178C6.svg?style=flat-square)](https://www.typescriptlang.org/) [![Bun](https://img.shields.io/badge/Bun-v1.4.0-blueviolet.svg?style=flat-square)](https://bun.sh/)
+[![Version](https://img.shields.io/badge/Version-0.8.0-blue.svg?style=flat-square)](./CHANGELOG.md) [![License](https://img.shields.io/badge/License-Apache%202.0-orange.svg?style=flat-square)](./LICENSE) [![Docker](https://img.shields.io/badge/Docker-ghcr.io-2496ED?style=flat-square&logo=docker&logoColor=white)](https://github.com/users/cyanheads/packages/container/package/eurostat-mcp-server) [![MCP SDK](https://img.shields.io/badge/MCP%20SDK-^2.0.0-green.svg?style=flat-square)](https://modelcontextprotocol.io/) [![npm](https://img.shields.io/npm/v/@cyanheads/eurostat-mcp-server?style=flat-square&logo=npm&logoColor=white)](https://www.npmjs.com/package/@cyanheads/eurostat-mcp-server) [![TypeScript](https://img.shields.io/badge/TypeScript-^7.0.2-3178C6.svg?style=flat-square)](https://www.typescriptlang.org/) [![Bun](https://img.shields.io/badge/Bun-v1.4.0-blueviolet.svg?style=flat-square)](https://bun.sh/)
 
 </div>
 
@@ -31,7 +29,9 @@
 
 ## Overview
 
-EU statistics from the Eurostat catalogue — economy, demography, trade, health, and NUTS regional data. Search and browse the catalogue by keyword or theme, inspect dataset dimensions, and query a slice or bulk-download a whole dataset from any MCP client. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.
+EU statistics from the Eurostat catalogue: economy, demography, trade, health, and NUTS regional data. Search and browse the catalogue by keyword or theme, inspect dataset dimensions, then query a slice or bulk-download a whole dataset. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.
+
+The catalogue spans two Eurostat hosts. Most datasets come from the dissemination API; the `DS-*` collections — detailed trade by CN8, HS, SITC, BEC and CPA (Comext), and PRODCOM industrial production — come from the Comext dissemination host. Every tool routes a `DS-*` code there by its prefix, in any case, so the same calls work on both.
 
 ### Tools
 
@@ -45,99 +45,91 @@ Two of the eight are listed only when the dataframe canvas is enabled (`CANVAS_P
 | `eurostat_get_dimension_values` | List all valid codes for one dataset dimension, with NUTS hierarchy filtering for `geo` |
 | `eurostat_query_dataset` | Fetch a bounded preview of decoded observations with dimension filters, NUTS geo-level, and time-range controls |
 | `eurostat_download_dataset` | Download a whole dataset via the SDMX bulk endpoint and stage every observation on the dataframe canvas |
-| `eurostat_dataframe_describe` | List the tables staged on a dataframe canvas, with row counts and column types — canvas only |
-| `eurostat_dataframe_query` | Run a read-only SQL SELECT across staged tables — canvas only |
+| `eurostat_dataframe_describe` | List the tables staged on a dataframe canvas, with row counts and column types |
+| `eurostat_dataframe_query` | Run a read-only SQL SELECT across staged tables |
 
 ### Resources
 
 | Resource | Description |
 |:---|:---|
-| `eurostat://dataset/{dataset_code}` | Dataset metadata (dimensions, time range, observation count, last-updated) by URI, for cache-injectable context |
+| `eurostat://dataset/{dataset_code}` | Dataset metadata (dimensions, time range, observation count, last-updated) by URI |
+
+The same metadata is available through `eurostat_get_dataset_info` for tool-only clients.
 
 ## Capability reference
 
 ### `eurostat_search_datasets` <sub>tool</sub>
 
-- Tokenized keyword match — whitespace-separated tokens are ANDed case-insensitively across each dataset's label, theme breadcrumb, and code, so word order and theme-named queries resolve without a verbatim label match
-- Returns `code`, `label`, `type` (dataset/table), period coverage, observation count, and theme breadcrumb per result
-- One row per dataset code — Eurostat files some datasets under multiple theme branches; matches are deduplicated so `totalMatches` and page slots count unique targets
-- Cursor pagination: `limit` (1–100, default 20) sets page size, `totalMatches` reports the full count, and passing `nextCursor` back as `cursor` pages through every match. A cursor is bound to its originating query and catalogue snapshot — reusing one with a different query, or after the catalogue refreshes, returns `invalid_cursor` instead of a silently shifted page
-- `nextStep` on each result names the next tool to call
-- Catalogue TOC is cached in memory for 12 hours (`EUROSTAT_TOC_CACHE_TTL_MS`), refreshed on the next call past that age
+- `query` tokens are ANDed case-insensitively across each dataset's label, theme breadcrumb, and code; `limit` 1–100 (default 20), paged by passing `nextCursor` back as `cursor`
+- Results carry `code`, `label`, `type` (`dataset` / `table`), period coverage, `obsCount`, `lastUpdated`, and `themePath`; `totalMatches` counts every match
+- Searches the dissemination table of contents plus the Comext host's dataflow list, whose `DS-*` entries carry `lastUpdated` but no period coverage or `obsCount`. A collection on neither, such as the legacy PRODCOM `DS-056120`, is not disseminated and cannot be reached
+- Fails as `no_match` — for a query naming such a `DS-*` code, saying the collection is not disseminated rather than suggesting a broader search — or `invalid_cursor` when a cursor is reused with a different query or after the catalogue refreshes
 
 ---
 
 ### `eurostat_browse_themes` <sub>tool</sub>
 
-- Without `theme_code`: returns the top-level theme folders (Economy, Population, Transport, etc.)
-- With `theme_code`: returns immediate children — subtheme folders and datasets in that branch
-- Each entry carries `code`, `label`, `type` (folder/dataset/table), data period, and observation count where available
-- Returns a breadcrumb `parentPath` from root to the current node, plus a `nextStep` hint suited to the level
-- One branch per folder code — Eurostat files a few folder codes under several branches; a code resolves to the branch listed first in the catalogue (never fewer children than the ones it shadows), and `otherPlacements` names those so the ambiguity is visible
+- Omit `theme_code` for the top-level theme folders; pass a folder code for its immediate children
+- The Comext collections sit in two folders the table of contents lacks: `ext_go_detail` (detailed trade) under `ext_go`, and `prom` (PRODCOM) under `icts`
+- Items carry `code`, `label`, `type` (`folder` / `dataset` / `table`), and `hasChildren`, with a `parentPath` breadcrumb; `otherPlacements` names other branches that file the same folder code
+- Fails as `not_found` for an unknown code, `not_a_folder` for a dataset or table code
 
 ---
 
 ### `eurostat_get_dataset_info` <sub>tool</sub>
 
-- Returns all dimensions with their codes, labels, and up to 10 sample values each
-- Dimension values reflect the full dataset-available set (including every period for `time`), not just what appears in populated observations
-- Reports overall time range and total observation count, each omitted — not zeroed — when Eurostat does not report it
-- For a dimension with more than 10 values, call `eurostat_get_dimension_values` for the full list
-- `metadataUrl` links to the ESMS metadata page when Eurostat provides one
+- One `dataset_code`; returns every dimension with `valuesCount` and up to 10 `sampleValues`, plus `timeRange`, `obsCount`, `lastUpdated`, and the ESMS `metadataUrl`
+- The Comext host reports no `timeRange` or `obsCount` for a `DS-*` collection, so both read as unreported. Its structure carries a label for every code, 23 MB for `DS-045409`: parsed metadata is cached per dataset for an hour, within a 64 MiB memory budget, so only the first call pays for it
+- Fails as `not_found` for an unknown dataset, or `upstream_fault` when Eurostat returns a structure or content constraint the server cannot read; a failed read is not cached, so a later call downloads it afresh
 
 ---
 
 ### `eurostat_get_dimension_values` <sub>tool</sub>
 
-- Returns the complete dataset-available set of codes and labels for any dimension, from the same content constraint `eurostat_get_dataset_info` uses
-- For `geo`, NUTS hierarchy filtering via `geo_level`: `aggregate`, `country` (default), `nuts1`, `nuts2`, `nuts3` — an empty level reports `no_results` rather than implying the dataset lacks data, and pairing `geo_level` with any other dimension is rejected
-- Verify codes here before `eurostat_query_dataset` or `eurostat_download_dataset` — an invalid dimension value returns no data silently from the former and a rejected fault from the latter
+- `dataset_code` plus `dimension`; returns the dataset-available code/label pairs in `values`, with `totalCount`
+- At most 2,000 values come back inline, in Eurostat's order. A longer list — the 37,069 CN8 codes of `DS-045409`, a daily `time` dimension, the largest airport-pair lists — is cut there, with `truncated`, `shown`, `cap`, and a `notice` saying where the rest is
+- For `geo`, `geo_level` picks a NUTS level (`aggregate`, `country` by default, `nuts1`, `nuts2`, `nuts3`)
+- `canvas_id` also stages every value, past the inline cap too, on that canvas as a `code` / `label` table (`canvasId` / `tableName` / `stagedRowCount`), to search with SQL or to label a download's code-only columns through a join; this tool never starts a canvas of its own, and ignores `canvas_id` on a deployment without one
+- Fails as `not_found` for an unknown dataset or dimension, `no_results` for a NUTS level with no values, `conflicting_params` for `geo_level` on any other dimension, `upstream_fault` for a structure or content constraint the server cannot read, or `canvas_not_found` for an unknown or expired `canvas_id`
 
 ---
 
 ### `eurostat_query_dataset` <sub>tool</sub>
 
-- Dimension filters as `{dimension_code: [values]}`; a `geo` filter and `geo_level` (NUTS: `aggregate`/`country`/`nuts1`/`nuts2`/`nuts3`) are mutually exclusive, as are `since_period`/`until_period` and `last_n_periods`; an empty filter array is dropped rather than applied
-- `preview_limit` (1–500, default 50) bounds only the inline prefix of decoded observations — it never changes `obsCount`, `missingObsCount`, `timeRange`, or what gets staged. There is deliberately no cursor or offset; filters and period controls are the only way to shrink the match itself
-- Each observation carries dimension code/label pairs, a nullable `value`, an optional OBS_FLAG `status` (e.g. `p`=provisional, `e`=estimated), and a separate optional `CONF_STATUS` `confStatus` marker — usually why a value is null
-- `truncated` is true only when the match exceeds the 5,000-observation staging threshold, independent of `preview_limit`. With the dataframe canvas enabled, a match above that threshold is staged whole as a SQL table (`canvasId` / `tableName` / `stagedRowCount`) — call `eurostat_dataframe_describe` before `eurostat_dataframe_query`; without a canvas those fields are absent and narrowing the query is the only way to reach the rest
-- `canvas_id` reuses an existing canvas so a result can be joined against earlier ones; an oversized unfiltered query is caught by async-response detection and returned as an actionable, non-retryable error instead of timing out
-- Fetches a slice — for a whole dataset, `eurostat_download_dataset` reads the SDMX bulk endpoint instead, at roughly half the bytes
+- `dataset_code` plus `filters` (`{dimension_code: [values]}`, codes in any case), `geo_level`, and either `since_period` / `until_period` (`YYYY`, `YYYY-MM`, `YYYY-MM-DD`, `YYYY-Qn`, `YYYY-Sn`, `YYYY-Tn`, `YYYY-Mnn`, `YYYY-Wnn`, `YYYY-Dnnn`; extra leading zeros after the letter are dropped, so `2020-Q01` is sent as `2020-Q1`, and `YYYY-A1` is sent as `YYYY`) or `last_n_periods`, which counts back from the dataset's latest period rather than the slice's; `preview_limit` 1–500 (default 50) sets the inline row count; `lang` is `EN`, `FR`, or `DE`
+- Each observation carries code/label pairs per dimension, a nullable `value`, an OBS_FLAG `status`, and a CONF_STATUS `confStatus`; `obsCount`, `missingObsCount`, and `timeRange` cover the whole match, `truncated` is true above 5,000 observations, and `unmatchedValues` names filter values that matched nothing
+- PRODCOM publishes its flag and unit indicators as text in the value itself: `:C` comes back as a null `value` with `confStatus` `C`, and anything else, such as the unit `KG`, verbatim in `valueText` with a null `value`
+- Fails as `not_found`, `no_results` (naming the filter values that matched nothing and, up to the newest 24 with a full count, the selected periods that carry no value), `invalid_dimension`, `invalid_period` (a malformed or non-existent period, or a `since_period` that starts after `until_period` ends, rejected before any request), `conflicting_params` (`geo` filter with `geo_level`, or a period range with `last_n_periods`), a non-retryable `async_response` for a query too large to serve inline, or `canvas_not_found` for an unknown or expired `canvas_id`
 
 ---
 
 ### `eurostat_download_dataset` <sub>tool</sub>
 
-- TSV bulk body runs 48–63% of the JSON-stat bytes `eurostat_query_dataset` reads for the same data — measured across four datasets from 1.1M to 12.8M observations
-- Filters take the same `{dimension_code: [values]}` map, applied server-side; the positional key needs every dimension in the dataset's own order, so a filter naming one the dataset lacks is rejected with the real dimension list rather than sent malformed
-- No `last_n_periods` here — only `since_period` / `until_period` actually shrink the response, since the TSV layout keeps a column per period regardless of selector
-- Byte budget (`EUROSTAT_BULK_MAX_BYTES`, default 50 MiB) is enforced while streaming — Eurostat sends no `Content-Length`, so a transfer stopped mid-flight returns its rows with `budgetExceeded: true` instead of an error
-- Failure modes are typed: an async queue ticket (Eurostat's too-costly-to-serve-inline response) is a non-retryable error; XML SOAP faults map to `not_found` (100), `filter_arity` (140), and `invalid_dimension` (150 — also covers an out-of-coverage period range), each with a recovery hint naming the next tool
-- With the dataframe canvas enabled, every observation is staged as a SQL table (`canvasId` / `tableName` / `stagedRowCount`), streamed row by row — call `eurostat_dataframe_describe` before `eurostat_dataframe_query`. Without a canvas, only `preview_limit` rows (default 50, max 500) survive the call; `rowCount` / `missingCount` / `periodRange` still describe the whole download
+- `dataset_code` plus the same `filters` map and `since_period` / `until_period` in the same period forms (no `last_n_periods`: the TSV keeps a column per period unless a range drops it); `preview_limit` 1–500 (default 50)
+- Returns `rowCount` (echoed as `totalCount`), `missingCount`, `periodRange`, and `bytesRead` for the whole download; the `EUROSTAT_BULK_MAX_BYTES` budget (default 50 MiB) stops a transfer mid-stream and returns what arrived with `budgetExceeded: true`
+- On a `DS-*` table, `obs_value_text` holds a value published as text (PRODCOM's `KG`), and a PRODCOM `:C` lands in `conf_status`
+- Fails as `not_found`, `invalid_dimension` (including a range wholly outside the dataset's coverage), `invalid_period` (a malformed or non-existent period, or a `since_period` that starts after `until_period` ends, rejected before any request), `filter_arity`, a non-retryable `async_queued` when Eurostat queues the extraction, a non-retryable `extraction_too_big` when Eurostat refuses it as too large (past its 5,000,000-row limit, or an unfiltered download of a large Comext collection) with the dimensions left to filter, `no_results` (including a range inside the dataset's coverage that misses the filtered series), `upstream_fault`, or `canvas_not_found` for an unknown or expired `canvas_id`
 
 ---
 
 ### `eurostat_dataframe_describe` <sub>tool</sub>
 
-- Lists tables staged on the canvas (from `canvas_id`, returned by `eurostat_query_dataset` or `eurostat_download_dataset`) with row counts, column names, types, and nullability — call before writing SQL, since the two stagers write different dimension columns
-- Also reports the canvas's and each table's `expiresAt`; every call against a canvas slides its lifetime forward (`CANVAS_TTL_MS`, default 24h)
-- Errors `canvas_disabled` when this deployment runs without a canvas, `canvas_not_found` when the ID is unknown or expired
+- `canvas_id` from a staging response; lists each table's `name`, `rowCount`, and typed columns, plus canvas and table `expiresAt` (sliding `CANVAS_TTL_MS`, default 24h); fails as `canvas_not_found` for an unknown or expired ID, or `canvas_disabled` on a deployment without a canvas
+- `eurostat_query_dataset` tables carry a code and a `_label` column per dimension; `eurostat_download_dataset` tables carry codes only, plus `time`. Both share `obs_value`, `obs_flag`, `obs_flag_label`, `conf_status`, and `conf_status_label`, so they join on dimension codes and `time`; a `DS-*` table from either adds `obs_value_text`
+- `eurostat_get_dimension_values` tables carry `code` and `label`: join one to a download on its dimension column (`d.geo = g.code`) to label it
 
 ---
 
 ### `eurostat_dataframe_query` <sub>tool</sub>
 
-- Runs a single read-only `SELECT` against staged tables; statement chaining, non-`SELECT` verbs, and functions that read files or external data are rejected with a typed error
-- `eurostat_query_dataset` tables carry a code column per dimension plus a `_label` companion; `eurostat_download_dataset` tables carry code columns only (no labels) plus a `time` column — both write the same five measure columns (`obs_value`, `obs_flag`, `obs_flag_label`, `conf_status`, `conf_status_label`) with matching codes, so tables from either stager join on dimension codes and `time`
-- A confidential cell reads `obs_flag = NULL` with `conf_status = 'C'` on either table — JSON-stat folds the two into one string (`|C`) that `eurostat_query_dataset` splits before staging
-- Results are bounded by `CANVAS_DEFAULT_ROW_LIMIT` (default 10,000); `truncated: true` means add a `LIMIT`, an aggregate, or a narrower `WHERE`. 64-bit integer results — `COUNT(*)` included — arrive as strings so values outside the JSON number range survive intact
-- The DuckDB binding ships with the server — `CANVAS_PROVIDER_TYPE=duckdb` is the only switch — except the one-click `.mcpb` bundle, which strips native bindings to stay portable; use the npm, Docker, or from-source install for SQL analytics
+- One read-only `SELECT` per call; chained statements, other verbs, and functions that read files or external data are rejected
+- Returns `columns`, `rows`, `rowCount`, and `truncated`, which is true past `CANVAS_DEFAULT_ROW_LIMIT` (default 10,000) rows; 64-bit integers, `COUNT(*)` included, arrive as strings. Fails as `missing_table`, `canvas_not_found`, or `canvas_disabled`
 
 ---
 
 ### `eurostat://dataset/{dataset_code}` <sub>resource</sub>
 
-- Same payload as `eurostat_get_dataset_info`, addressable as a resource URI for cache-injectable context
+- Same payload as `eurostat_get_dataset_info`, returned as `application/json`
 - `dataset_code` comes from `eurostat_search_datasets` or `eurostat_browse_themes`
 
 ## Features
@@ -146,18 +138,19 @@ Built on [`@cyanheads/mcp-ts-core`](https://github.com/cyanheads/mcp-ts-core): s
 
 Eurostat-specific:
 
-- NUTS hierarchy geo-level filtering (`aggregate` / `country` / `nuts1` / `nuts2` / `nuts3`) across `eurostat_query_dataset` and `eurostat_get_dimension_values`
-- OBS_FLAG (provisional, estimated, etc.) and CONF_STATUS (confidentiality) decoded into separate fields from Eurostat's combined encoding, consistent whether the observation came from JSON-stat or the bulk TSV
-- Async-response detection across every data-fetching tool — Eurostat's over-limit HTTP-200 warnings and HTTP-413/SOAP faults are classified into one typed, non-retryable error with filter guidance instead of surfacing as a timeout
-- SDMX 2.1 TSV bulk downloads at roughly half the JSON-stat byte cost, with a mid-transfer byte budget
-- Optional DuckDB dataframe canvas stages a query match above 5,000 observations, or a whole bulk download, as a queryable SQL table
+- The Statistics API (JSON-stat 2.0) for slices, the SDMX 2.1 TSV bulk endpoint for whole datasets at roughly half the bytes, and the catalogue TOC cached in memory for 12 hours
+- The Comext host's `DS-*` collections through the same tools: detailed trade by CN8, HS, SITC, BEC and CPA, and PRODCOM. The trade flows mix annual and monthly series in one dataset, so filter `freq`; `product`, `reporter` and `partner` carry aggregates (`TOTAL`, `EU27_2020`, `EXT_EU27_2020`) that double-count when summed with their members. The Comext host serves no large collection unfiltered
+- NUTS geo-level filtering (`aggregate` / `country` / `nuts1` / `nuts2` / `nuts3`) on `eurostat_query_dataset` and `eurostat_get_dimension_values`
+- OBS_FLAG (provisional, estimated, and so on) and CONF_STATUS (confidentiality) decoded into separate fields, with the same codes from JSON-stat and the bulk TSV
+- Eurostat's too-large-to-serve responses (HTTP-200 async warnings, HTTP 413, SOAP fault 413, SOAP queue tickets) come back as non-retryable `async_response`, `extraction_too_big`, or `async_queued` errors that name the dataset's own dimensions left to filter, not timeouts
+- Inline rows are capped by `preview_limit` (at most 500). With `CANVAS_PROVIDER_TYPE=duckdb`, a query match above 5,000 observations, or any bulk download, is staged whole as a SQL table (`canvasId` / `tableName` / `stagedRowCount`) for the dataframe tools, and `canvas_id` stages the next result beside earlier ones for joins — including a dimension's code/label list from `eurostat_get_dimension_values`, which labels a bulk table's codes. An empty download fails as `no_results` without creating or touching a canvas. The `.mcpb` bundle strips the native DuckDB binding, so SQL analytics need the npm, Docker, or from-source install
 
 Agent-friendly output:
 
-- Structured error contracts — every declared failure carries a typed `reason` and a `recovery.hint` naming the exact next tool to call, not just an error string
-- Next-step hints — `eurostat_search_datasets` and `eurostat_browse_themes` responses carry a `nextStep` field pointing at the right follow-up call
-- Omitted-vs-unknown fields — counts and period bounds Eurostat doesn't report (`obsCount`, `timeRange.start`/`end`, `lastUpdated`) are omitted from the response rather than defaulted to zero or blank
-- Truncation and staging notices — a response that exceeds an inline cap carries an enrichment notice naming the exact `eurostat_dataframe_describe` → `eurostat_dataframe_query` follow-up
+- Typed error contracts: every declared failure carries a `reason` and a `recovery.hint` naming the next tool to call
+- Next-step hints: `eurostat_search_datasets` and `eurostat_browse_themes` return a `nextStep` pointing at the follow-up call
+- Unknown stays unknown: counts and period bounds Eurostat doesn't report (`obsCount`, `timeRange.start` / `end`, `lastUpdated`) are omitted rather than zeroed
+- Effective-query echo: `appliedFilters` on `eurostat_query_dataset` and `appliedQuery` (with the SDMX `url`) on `eurostat_download_dataset`, plus a `notice` when the inline preview omits rows, naming the staged table when there is one; `eurostat_query_dataset`'s `notice` also names any filter value that matched nothing
 
 ## Getting started
 
@@ -237,7 +230,8 @@ MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
 
 ### Prerequisites
 
-- [Bun v1.4.0](https://bun.sh/) or higher. No API key required — Eurostat's dissemination API is public.
+- [Bun v1.4.0](https://bun.sh/) or higher (or Node.js v24+).
+- No API key: Eurostat's dissemination API and its Comext host are public.
 
 ### Installation
 
@@ -259,32 +253,34 @@ cd eurostat-mcp-server
 bun install
 ```
 
-## Configuration
+4. **Configure environment (optional, every setting has a default):**
 
-All configuration is validated at startup via Zod schemas in `src/config/server-config.ts`. Key environment variables:
+```sh
+cp .env.example .env
+```
+
+## Configuration
 
 | Variable | Description | Default |
 |:---|:---|:---|
-| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http` | `stdio` |
-| `MCP_HTTP_PORT` | HTTP server port | `3010` |
-| `MCP_HTTP_ENDPOINT_PATH` | HTTP endpoint path | `/mcp` |
-| `MCP_PUBLIC_URL` | Public origin override for TLS-terminating reverse-proxy deployments | none |
-| `MCP_SESSION_MODE` | HTTP session posture: `auto`, `stateful`, or `stateless` (`auto` resolves to `stateful`). The server declares `stateless` in `createApp()`; an explicitly set value overrides that default. | `stateless` |
-| `MCP_AUTH_MODE` | Authentication: `none`, `jwt`, or `oauth` | `none` |
-| `MCP_LOG_LEVEL` | Log level (`debug`, `info`, `warning`, `error`, etc.) | `info` |
-| `MCP_GC_PRESSURE_INTERVAL_MS` | Opt-in Bun-only forced-GC pressure loop (ms). Recommended starting point if heap growth is observed: `60000`. | `0` (disabled) |
-| `LOGS_DIR` | Directory for log files (Node.js only) | `<project-root>/logs` |
-| `STORAGE_PROVIDER_TYPE` | Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1` | `in-memory` |
-| `EUROSTAT_BASE_URL` | Eurostat API base URL | `https://ec.europa.eu/eurostat/api/dissemination` |
-| `EUROSTAT_REQUEST_TIMEOUT_MS` | HTTP request timeout in ms | `30000` |
-| `EUROSTAT_TOC_CACHE_TTL_MS` | Catalogue TOC cache lifetime in ms — the first search or browse call past this age refreshes it | `43200000` (12 hours) |
-| `EUROSTAT_BULK_TIMEOUT_MS` | HTTP timeout for one `eurostat_download_dataset` transfer in ms — held separate because a bulk body streams for minutes | `120000` (2 minutes) |
-| `EUROSTAT_BULK_MAX_BYTES` | Byte budget for one bulk download, counted on the decoded TSV and enforced while streaming | `52428800` (50 MiB) |
-| `CANVAS_PROVIDER_TYPE` | `duckdb` enables the dataframe canvas: lists the two dataframe tools, lets `eurostat_query_dataset` stage a match above 5,000 observations, and lets `eurostat_download_dataset` retain a bulk download | `none` |
-| `CANVAS_TEMP_PATH` | Directory DuckDB writes canvas spill files to. Must be writable by the server process | `<os tmpdir>/mcp-canvas` |
-| `CANVAS_TTL_MS` | Sliding lifetime of a staged canvas in ms; every call against it extends the window | `86400000` (24 hours) |
-| `CANVAS_DEFAULT_ROW_LIMIT` | Max rows one `eurostat_dataframe_query` returns before reporting `truncated` | `10000` |
-| `OTEL_ENABLED` | Enable OpenTelemetry | `false` |
+| `EUROSTAT_BASE_URL` | Eurostat API base URL. | `https://ec.europa.eu/eurostat/api/dissemination` |
+| `EUROSTAT_COMEXT_BASE_URL` | Comext dissemination host, which serves every `DS-*` dataset code (detailed trade and PRODCOM). | `https://ec.europa.eu/eurostat/api/comext/dissemination` |
+| `EUROSTAT_REQUEST_TIMEOUT_MS` | HTTP request timeout, in ms. | `30000` |
+| `EUROSTAT_METADATA_TIMEOUT_MS` | Timeout for one dataset's SDMX dataflow structure, in ms — 23 MB, uncompressed, for `DS-045409`. | `120000` (2 min) |
+| `EUROSTAT_TOC_CACHE_TTL_MS` | Catalogue TOC cache lifetime, in ms; the first search or browse call past it refreshes the TOC. | `43200000` (12 h) |
+| `EUROSTAT_BULK_TIMEOUT_MS` | Timeout for one `eurostat_download_dataset` transfer, in ms. | `120000` (2 min) |
+| `EUROSTAT_BULK_MAX_BYTES` | Byte budget for one bulk download, counted on the decoded TSV and enforced while streaming. | `52428800` (50 MiB) |
+| `CANVAS_PROVIDER_TYPE` | `duckdb` enables the dataframe canvas: lists the two dataframe tools and turns on staging. | `none` |
+| `CANVAS_TTL_MS` | Sliding lifetime of a staged canvas, in ms. | `86400000` (24 h) |
+| `CANVAS_DEFAULT_ROW_LIMIT` | Max rows one `eurostat_dataframe_query` returns before reporting `truncated`. | `10000` |
+| `MCP_TRANSPORT_TYPE` | Transport: `stdio` or `http`. | `stdio` |
+| `MCP_HTTP_PORT` | HTTP server port. | `3010` |
+| `MCP_SESSION_MODE` | HTTP session mode: `stateless`, `stateful`, or `auto`. The server declares `stateless`; a set value overrides it. | `stateless` |
+| `MCP_AUTH_MODE` | Authentication: `none`, `jwt`, or `oauth`. | `none` |
+| `MCP_LOG_LEVEL` | Log level (`debug`, `info`, `warning`, `error`, etc.). The Docker image sets `info`. | `debug` |
+| `LOGS_DIR` | Directory for log files (Node.js only). | `<project-root>/logs` |
+| `STORAGE_PROVIDER_TYPE` | Storage backend: `in-memory`, `filesystem`, `supabase`, `cloudflare-kv/r2/d1`. | `in-memory` |
+| `OTEL_ENABLED` | Enable [OpenTelemetry](https://github.com/cyanheads/mcp-ts-core/tree/main/docs/telemetry). | `false` |
 
 See [`.env.example`](./.env.example) for the full list of optional overrides.
 
@@ -324,12 +320,16 @@ The Dockerfile defaults to HTTP transport, stateless session mode, and logs to `
 
 | Directory | Purpose |
 |:---|:---|
-| `src/index.ts` | `createApp()` entry point — registers tools and resources and inits services. |
-| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). Six tools for discovery and data access, plus two canvas-gated dataframe tools. |
+| `src/index.ts` | `createApp()` entry point — registers tools and the resource, inits services, gates the dataframe tools on the canvas. |
+| `src/mcp-server/tools` | Tool definitions (`*.tool.ts`). Six discovery and data tools, plus two canvas-gated dataframe tools. |
 | `src/mcp-server/resources` | Resource definitions. Dataset metadata resource. |
-| `src/services/eurostat-catalogue` | Catalogue service — fetches and parses the Eurostat TOC TXT file; TTL-bounded in-memory cache. |
-| `src/services/eurostat-data` | Data service — dataset-scoped SDMX metadata parser plus Statistics API querying, JSON-stat 2.0 decoding, async-response detection, and dataframe row source. |
-| `src/services/canvas-accessor.ts` | Module-level accessor for the optional DataCanvas, plus the acquire helper that names the misconfigured path on a permission failure. |
+| `src/services/eurostat-catalogue` | Catalogue service — fetches and parses the Eurostat TOC, merges the Comext dataflow list into it, with a TTL-bounded in-memory cache. |
+| `src/services/eurostat-data` | Statistics API service — SDMX metadata parsing with a per-dataset cache, JSON-stat 2.0 decoding, async-response detection, canvas row source. |
+| `src/services/eurostat-bulk` | SDMX 2.1 TSV bulk service — streaming download, byte budget, SOAP fault mapping, canvas row source. |
+| `src/services/eurostat-codelists.ts` | OBS_FLAG and CONF_STATUS codelists, the measure column names both stagers write, and the text-value decoder. |
+| `src/services/eurostat-hosts.ts` | Which host serves a dataset code: `DS-*` to the Comext host, everything else to the main one. |
+| `src/services/canvas-accessor.ts` | Accessor for the optional DataCanvas and the acquire helper canvas-touching tools share. |
+| `src/services/shared-load.ts` | Lets concurrent callers await one shared download, so one caller's cancellation releases only that caller. |
 | `src/config` | Server-specific environment variable parsing and validation with Zod. |
 | `tests/` | Unit and integration tests, mirroring the `src/` structure. |
 
@@ -339,7 +339,7 @@ See [`CLAUDE.md`](./CLAUDE.md) for development guidelines and architectural rule
 
 - Handlers throw, framework catches — no `try/catch` in tool logic
 - Use `ctx.log` for logging, `ctx.state` for storage
-- Register new tools and resources in the `createApp()` arrays
+- Register new tools and resources in the `createApp()` arrays in `src/index.ts`
 - Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields
 
 ## Contributing

package/changelog/0.7.x/0.7.0.md

@@ -0,0 +1,33 @@
+---
+summary: "Both data tools now reject malformed, non-existent, and inverted period ranges as invalid_period before any request; eurostat_query_dataset explains an empty match and names filter values that matched nothing; eurostat_download_dataset reports totalCount instead of truncated."
+breaking: true
+security: false
+---
+
+# 0.7.0 — 2026-09-25
+
+## Added
+
+- **`invalid_period` on `eurostat_query_dataset` and `eurostat_download_dataset`** ([#47](https://github.com/cyanheads/eurostat-mcp-server/issues/47), [#53](https://github.com/cyanheads/eurostat-mcp-server/issues/53)). `since_period`/`until_period` are checked in the handler before any request: the literal must be an accepted form, every month, quarter, semester, trimester, week, and day it names must exist, and `since_period` must not start after `until_period` ends. Cross-frequency pairs such as `2020-06` to `2020` stay valid.
+- **`unmatchedValues` on `eurostat_query_dataset`** ([#52](https://github.com/cyanheads/eurostat-mcp-server/issues/52)) — filter values that matched nothing, keyed by dimension and spelled as sent. `notice` and the text output name them too; omitted when every value matched.
+- **`no_results` diagnosis on `eurostat_query_dataset`** ([#48](https://github.com/cyanheads/eurostat-mcp-server/issues/48)) — read from the empty reply with no extra request: `data.unmatchedValues`, and `data.matchedPeriods` (the newest 24 selected periods, none carrying a value) with `data.matchedPeriodCount`. The message and hint name the cause: an unmatched value, a range outside the dataset's coverage (with its oldest and latest period), `last_n_periods` counting back past the slice's latest period, or a combination that carries no data.
+
+## Changed
+
+- **Breaking: `eurostat_download_dataset` enrichment drops `truncated`, `shown`, and `cap`, and adds `totalCount`** ([#49](https://github.com/cyanheads/eurostat-mcp-server/issues/49)), equal to `rowCount`. A preview shorter than the download is disclosed as a `notice` sentence; `budgetExceeded` remains the only signal that the download is incomplete.
+- **Breaking: period literals that name a component that does not exist fail as `invalid_period`** ([#47](https://github.com/cyanheads/eurostat-mcp-server/issues/47), [#53](https://github.com/cyanheads/eurostat-mcp-server/issues/53)) instead of reaching Eurostat, which rolled some into a neighbouring period (`2020-13`, `2020-Q5`, `2021-W53`, `2021-02-29`). An inverted range (`since_period` `2024-01` with `until_period` `2020-01`), which Eurostat answered with data outside it, fails the same way.
+- **Breaking: period faults move to `invalid_period`** ([#47](https://github.com/cyanheads/eurostat-mcp-server/issues/47)) from `conflicting_params` on `eurostat_query_dataset` and from `filter_arity` on `eurostat_download_dataset`. Bulk fault 140 is split on its fault string: `TIME_PERIOD_FILTER_SPEC_INVALID` maps to `invalid_period`, `INVALID_QUERY_NB_FILTERS` stays `filter_arity`.
+- **Breaking: an upper-case filter key with `geo_level` fails as `conflicting_params`** ([#54](https://github.com/cyanheads/eurostat-mcp-server/issues/54)); `GEO` previously bypassed the check.
+- **Filter keys match dimension codes in any case** on both data tools ([#54](https://github.com/cyanheads/eurostat-mcp-server/issues/54)). `eurostat_download_dataset` places `GEO` at `geo` instead of rejecting it, and keys that differ only in case pool their values.
+- **Period literals are sent in canonical form** and echoed that way in `appliedFilters`/`appliedQuery`: extra leading zeros after the letter are dropped (`2020-Q01` → `2020-Q1`), a day of the year is sent as three digits (`2026-D1` → `2026-D001`), and `YYYY-A1` is sent as `YYYY`.
+- **`eurostat_dataframe_describe` and `eurostat_dataframe_query` recovery hints** name both staging tools for an unknown or expired canvas or table.
+- **Tool descriptions and docs**: `last_n_periods` states it counts back from the dataset's latest period, not the slice's; `eurostat_get_dimension_values` states how each data tool reports an invalid code — named in `unmatchedValues` or the `no_results` error by `eurostat_query_dataset`, a fault on `eurostat_download_dataset`; the README capability reference, Features list, and configuration table are rewritten to match current behavior.
+
+## Fixed
+
+- **`eurostat_download_dataset`'s no-canvas notice** ([#49](https://github.com/cyanheads/eurostat-mcp-server/issues/49)) no longer recommends a narrower query when every row came back inline, and names the `preview_limit` that returns them all when the download holds 500 rows or fewer.
+- **`eurostat_download_dataset`'s `no_results` hint** ([#47](https://github.com/cyanheads/eurostat-mcp-server/issues/47)) also names a `since_period`/`until_period` range that misses the filtered series — one inside the dataset's coverage, which downloads as an empty table (a range wholly outside it fails as `invalid_dimension`).
+
+## Dependencies
+
+- `@socketsecurity/bun-security-scanner` (dev) `^1.1.2` → `^1.1.3`

package/changelog/0.8.x/0.8.0.md

@@ -0,0 +1,30 @@
+---
+summary: "Every tool now reaches Eurostat's Comext host for the DS-* detailed-trade and PRODCOM collections, and eurostat_get_dimension_values caps inline values at 2,000 while staging the full list as a code/label table on a caller's canvas."
+breaking: true
+security: false
+---
+
+# 0.8.0 — 2026-09-25
+
+## Added
+
+- **Comext `DS-*` collections on every tool** ([#46](https://github.com/cyanheads/eurostat-mcp-server/issues/46)). A dataset code starting `DS-`, in any case, is routed to the Comext dissemination host: detailed trade by CN8, HS, SITC, BEC and CPA, and PRODCOM. Comext entries report `lastUpdated` but no period coverage or observation count.
+- **Comext dataflows in the catalogue** ([#46](https://github.com/cyanheads/eurostat-mcp-server/issues/46)). `eurostat_search_datasets` and `eurostat_browse_themes` merge the Comext dataflow list into the table of contents, under `ext_go_detail` (in `ext_go`) and `prom` (in `icts`); a failed Comext fetch leaves the catalogue answering from the table of contents alone.
+- **`canvas_id` on `eurostat_get_dimension_values`** ([#50](https://github.com/cyanheads/eurostat-mcp-server/issues/50)) stages the dimension's whole value list as a `code` / `label` table on that canvas, returned as `canvasId` / `tableName` / `stagedRowCount`, to label a download's code columns through a join. The tool never starts a canvas; an unknown or expired `canvas_id` fails as `canvas_not_found`.
+- **`valueText` on `eurostat_query_dataset` observations, and `obs_value_text` on `DS-*` staged tables** from either data tool, holding a value Eurostat published as text (PRODCOM's unit `KG`) beside a null `value` / `obs_value`. PRODCOM's `:C` decodes to `confStatus` / `conf_status` `C`.
+- **`EUROSTAT_COMEXT_BASE_URL`** (default `https://ec.europa.eu/eurostat/api/comext/dissemination`) and **`EUROSTAT_METADATA_TIMEOUT_MS`** (default `120000`), the timeout for one dataset's SDMX dataflow structure: 23 MB for `DS-045409`.
+
+## Changed
+
+- **Breaking: `eurostat_get_dimension_values` returns at most 2,000 values inline** ([#50](https://github.com/cyanheads/eurostat-mcp-server/issues/50)), with `truncated`, `shown`, `cap`, and a `notice` saying where the rest are; `totalCount` still counts every value. Seven main-host lists are cut: `time` on `ert_bil_eur_d`, `ert_h_eur_d` and `irt_euryld_d`, and `airp_pr` on `avia_par_uk`, `avia_par_de`, `avia_par_it` and `avia_par_es`. Pass `canvas_id` to stage the full list.
+- **Breaking: `eurostat_download_dataset` maps SDMX fault 413 to non-retryable `extraction_too_big`**, not `upstream_fault`, on either host. The hint names the dataset's dimensions the request left unfiltered.
+- **Breaking: `eurostat_get_dataset_info` and `eurostat_get_dimension_values` no longer declare `async_response`; both declare `upstream_fault`** ([#58](https://github.com/cyanheads/eurostat-mcp-server/issues/58)) for a structure or content constraint the server cannot read.
+- **`eurostat_query_dataset`'s `async_response` hint names the dataset's own unfiltered dimensions**, and the message carries Eurostat's `EXTRACTION_TOO_BIG` label for an HTTP-413 refusal.
+- **Dataset metadata is cached per dataset for an hour**, within a 64 MiB budget, so repeat `eurostat_get_dataset_info` and `eurostat_get_dimension_values` calls skip the structure download; a failed read is not cached.
+- **Tool descriptions and server instructions** state where the Comext and main-host catalogues end ([#45](https://github.com/cyanheads/eurostat-mcp-server/issues/45)). A query naming a `DS-*` code on neither list, such as the legacy `DS-056120`, fails `no_match` saying the collection is not disseminated.
+
+## Fixed
+
+- **A filtered `eurostat_download_dataset` no longer fails on datasets whose latest period exceeds Eurostat's 5,000,000-row extraction limit** ([#57](https://github.com/cyanheads/eurostat-mcp-server/issues/57)) (`earn_ses_annual`). Key order is read from the dataset's structure definition instead of a one-period observation request.
+- **An empty `eurostat_download_dataset` fails `no_results` without creating or touching a canvas** ([#56](https://github.com/cyanheads/eurostat-mcp-server/issues/56)); it previously staged a 0-row table on a fresh or caller-supplied canvas.
+- **Cancelling one catalogue or metadata call no longer aborts the shared load** other concurrent callers are waiting on.

package/dist/config/server-config.d.ts

@@ -5,7 +5,9 @@
 import { z } from '@cyanheads/mcp-ts-core';
 declare const ServerConfigSchema: z.ZodObject<{
     baseUrl: z.ZodDefault<z.ZodString>;
+    comextBaseUrl: z.ZodDefault<z.ZodString>;
     requestTimeoutMs: z.ZodDefault<z.ZodCoercedNumber<unknown>>;
+    metadataTimeoutMs: z.ZodDefault<z.ZodCoercedNumber<unknown>>;
     tocCacheTtlMs: z.ZodDefault<z.ZodCoercedNumber<unknown>>;
     bulkTimeoutMs: z.ZodDefault<z.ZodCoercedNumber<unknown>>;
     bulkMaxBytes: z.ZodDefault<z.ZodCoercedNumber<unknown>>;

package/dist/config/server-config.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"server-config.d.ts","sourceRoot":"","sources":["../../src/config/server-config.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAG3C,QAAA,MAAM,kBAAkB;;;;;;iBAoCtB,CAAC;AAIH,wBAAgB,eAAe,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,kBAAkB,CAAC,CASpE"}
+{"version":3,"file":"server-config.d.ts","sourceRoot":"","sources":["../../src/config/server-config.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAG3C,QAAA,MAAM,kBAAkB;;;;;;;;iBAmDtB,CAAC;AAIH,wBAAgB,eAAe,IAAI,CAAC,CAAC,KAAK,CAAC,OAAO,kBAAkB,CAAC,CAWpE"}

package/dist/config/server-config.js

@@ -10,12 +10,23 @@ const ServerConfigSchema = z.object({
         .url()
         .default('https://ec.europa.eu/eurostat/api/dissemination')
         .describe('Eurostat API base URL'),
+    comextBaseUrl: z
+        .string()
+        .url()
+        .default('https://ec.europa.eu/eurostat/api/comext/dissemination')
+        .describe('Base URL of the Comext dissemination host, which serves the DS-* collections (detailed trade and PRODCOM) the main host does not. Every dataset code starting "DS-", in any case, is routed here.'),
     requestTimeoutMs: z.coerce
         .number()
         .int()
         .positive()
         .default(30_000)
         .describe('HTTP request timeout in milliseconds'),
+    metadataTimeoutMs: z.coerce
+        .number()
+        .int()
+        .positive()
+        .default(120_000)
+        .describe("HTTP timeout for one dataset's SDMX dataflow structure, in milliseconds. Held separate from EUROSTAT_REQUEST_TIMEOUT_MS because the structure carries a label for every code the dataset uses: 23 MB, uncompressed, for the CN8 trade collection DS-045409. Defaults to 2 minutes."),
     tocCacheTtlMs: z.coerce
         .number()
         .int()
@@ -39,7 +50,9 @@ let _config;
 export function getServerConfig() {
     _config ??= parseEnvConfig(ServerConfigSchema, {
         baseUrl: 'EUROSTAT_BASE_URL',
+        comextBaseUrl: 'EUROSTAT_COMEXT_BASE_URL',
         requestTimeoutMs: 'EUROSTAT_REQUEST_TIMEOUT_MS',
+        metadataTimeoutMs: 'EUROSTAT_METADATA_TIMEOUT_MS',
         tocCacheTtlMs: 'EUROSTAT_TOC_CACHE_TTL_MS',
         bulkTimeoutMs: 'EUROSTAT_BULK_TIMEOUT_MS',
         bulkMaxBytes: 'EUROSTAT_BULK_MAX_BYTES',

package/dist/config/server-config.js.map

@@ -1 +1 @@
-{"version":3,"file":"server-config.js","sourceRoot":"","sources":["../../src/config/server-config.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAC3C,OAAO,EAAE,cAAc,EAAE,MAAM,+BAA+B,CAAC;AAE/D,MAAM,kBAAkB,GAAG,CAAC,CAAC,MAAM,CAAC;IAClC,OAAO,EAAE,CAAC;SACP,MAAM,EAAE;SACR,GAAG,EAAE;SACL,OAAO,CAAC,iDAAiD,CAAC;SAC1D,QAAQ,CAAC,uBAAuB,CAAC;IACpC,gBAAgB,EAAE,CAAC,CAAC,MAAM;SACvB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,MAAM,CAAC;SACf,QAAQ,CAAC,sCAAsC,CAAC;IACnD,aAAa,EAAE,CAAC,CAAC,MAAM;SACpB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,UAAU,CAAC;SACnB,QAAQ,CACP,qLAAqL,CACtL;IACH,aAAa,EAAE,CAAC,CAAC,MAAM;SACpB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,OAAO,CAAC;SAChB,QAAQ,CACP,mNAAmN,CACpN;IACH,YAAY,EAAE,CAAC,CAAC,MAAM;SACnB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,UAAU,CAAC;SACnB,QAAQ,CACP,0QAA0Q,CAC3Q;CACJ,CAAC,CAAC;AAEH,IAAI,OAAuD,CAAC;AAE5D,MAAM,UAAU,eAAe;IAC7B,OAAO,KAAK,cAAc,CAAC,kBAAkB,EAAE;QAC7C,OAAO,EAAE,mBAAmB;QAC5B,gBAAgB,EAAE,6BAA6B;QAC/C,aAAa,EAAE,2BAA2B;QAC1C,aAAa,EAAE,0BAA0B;QACzC,YAAY,EAAE,yBAAyB;KACxC,CAAC,CAAC;IACH,OAAO,OAAO,CAAC;AACjB,CAAC"}
+{"version":3,"file":"server-config.js","sourceRoot":"","sources":["../../src/config/server-config.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAC3C,OAAO,EAAE,cAAc,EAAE,MAAM,+BAA+B,CAAC;AAE/D,MAAM,kBAAkB,GAAG,CAAC,CAAC,MAAM,CAAC;IAClC,OAAO,EAAE,CAAC;SACP,MAAM,EAAE;SACR,GAAG,EAAE;SACL,OAAO,CAAC,iDAAiD,CAAC;SAC1D,QAAQ,CAAC,uBAAuB,CAAC;IACpC,aAAa,EAAE,CAAC;SACb,MAAM,EAAE;SACR,GAAG,EAAE;SACL,OAAO,CAAC,wDAAwD,CAAC;SACjE,QAAQ,CACP,mMAAmM,CACpM;IACH,gBAAgB,EAAE,CAAC,CAAC,MAAM;SACvB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,MAAM,CAAC;SACf,QAAQ,CAAC,sCAAsC,CAAC;IACnD,iBAAiB,EAAE,CAAC,CAAC,MAAM;SACxB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,OAAO,CAAC;SAChB,QAAQ,CACP,oRAAoR,CACrR;IACH,aAAa,EAAE,CAAC,CAAC,MAAM;SACpB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,UAAU,CAAC;SACnB,QAAQ,CACP,qLAAqL,CACtL;IACH,aAAa,EAAE,CAAC,CAAC,MAAM;SACpB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,OAAO,CAAC;SAChB,QAAQ,CACP,mNAAmN,CACpN;IACH,YAAY,EAAE,CAAC,CAAC,MAAM;SACnB,MAAM,EAAE;SACR,GAAG,EAAE;SACL,QAAQ,EAAE;SACV,OAAO,CAAC,UAAU,CAAC;SACnB,QAAQ,CACP,0QAA0Q,CAC3Q;CACJ,CAAC,CAAC;AAEH,IAAI,OAAuD,CAAC;AAE5D,MAAM,UAAU,eAAe;IAC7B,OAAO,KAAK,cAAc,CAAC,kBAAkB,EAAE;QAC7C,OAAO,EAAE,mBAAmB;QAC5B,aAAa,EAAE,0BAA0B;QACzC,gBAAgB,EAAE,6BAA6B;QAC/C,iBAAiB,EAAE,8BAA8B;QACjD,aAAa,EAAE,2BAA2B;QAC1C,aAAa,EAAE,0BAA0B;QACzC,YAAY,EAAE,yBAAyB;KACxC,CAAC,CAAC;IACH,OAAO,OAAO,CAAC;AACjB,CAAC"}

package/dist/index.js

@@ -55,7 +55,8 @@ await createApp({
     instructions: `Eurostat MCP server — EU statistical data across the Eurostat catalogue.
 Workflow: eurostat_search_datasets or eurostat_browse_themes to find a dataset code → eurostat_get_dataset_info to see dimensions → eurostat_get_dimension_values to list valid filter values → eurostat_query_dataset to fetch observations.
 Apply dimension filters to keep queries small: an unfiltered query on a large dataset is slow and can return an async response error instead of data.
-Two paths past eurostat_query_dataset's 5,000-observation inline cap. For a slice of a dataset, keep using eurostat_query_dataset: when the match is larger than the cap and this deployment runs a dataframe canvas, the whole match is also staged as a SQL table named in the response. For a whole dataset, use eurostat_download_dataset, which reads the SDMX bulk endpoint instead — about half the bytes — and stages every observation the same way, bounded by a byte budget it reports back. Read either staged table with eurostat_dataframe_query (eurostat_dataframe_describe lists the table and column names); the two stage different column sets, since the bulk endpoint carries dimension codes with no labels.
+The catalogue covers two hosts. Most datasets come from the Eurostat dissemination table of contents; the DS-* codes — detailed trade by CN8, HS, SITC, BEC and CPA, and PRODCOM — come from the Comext host, and every tool routes a DS-* code there by its prefix. Comext collections are large: filter every request (freq included, since the trade flows mix annual and monthly series), and expect eurostat_get_dimension_values to return only the first 2,000 values of a long list inline. A collection on neither host, such as the legacy DS-056120, is not disseminated.
+Two paths past eurostat_query_dataset's 5,000-observation inline cap. For a slice of a dataset, keep using eurostat_query_dataset: when the match is larger than the cap and this deployment runs a dataframe canvas, the whole match is also staged as a SQL table named in the response. For a whole dataset, use eurostat_download_dataset, which reads the SDMX bulk endpoint instead — about half the bytes — and stages every observation the same way, bounded by a byte budget it reports back. Read either staged table with eurostat_dataframe_query (eurostat_dataframe_describe lists the table and column names); the two stage different column sets, since the bulk endpoint carries dimension codes with no labels. To label a download's codes, pass its canvasId to eurostat_get_dimension_values as canvas_id: the dimension's values are staged beside it as a code/label table to join on.
 The dataframe tools are not listed when the canvas is off. There, narrowing the filters is what brings a capped match into reach, and eurostat_download_dataset retains only its inline preview.`,
     landing: { requireAuth: false },
     setup(core) {

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AACA;;;GAGG;AAEH,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,+BAA+B,CAAC;AACvD,OAAO,EAAE,uBAAuB,EAAE,MAAM,iEAAiE,CAAC;AAC1G,OAAO,EAAE,oBAAoB,EAAE,MAAM,+DAA+D,CAAC;AACrG,OAAO,EAAE,yBAAyB,EAAE,MAAM,oEAAoE,CAAC;AAC/G,OAAO,EAAE,sBAAsB,EAAE,MAAM,iEAAiE,CAAC;AACzG,OAAO,EAAE,uBAAuB,EAAE,MAAM,kEAAkE,CAAC;AAC3G,OAAO,EAAE,sBAAsB,EAAE,MAAM,kEAAkE,CAAC;AAC1G,OAAO,EAAE,0BAA0B,EAAE,MAAM,sEAAsE,CAAC;AAClH,OAAO,EAAE,oBAAoB,EAAE,MAAM,+DAA+D,CAAC;AACrG,OAAO,EAAE,sBAAsB,EAAE,MAAM,iEAAiE,CAAC;AACzG,OAAO,EAAE,SAAS,EAAE,MAAM,+BAA+B,CAAC;AAC1D,OAAO,EAAE,uBAAuB,EAAE,MAAM,mDAAmD,CAAC;AAC5F,OAAO,EAAE,4BAA4B,EAAE,MAAM,6DAA6D,CAAC;AAC3G,OAAO,EAAE,uBAAuB,EAAE,MAAM,mDAAmD,CAAC;AAE5F;;;;;;;GAOG;AACH,MAAM,aAAa,GAAG,MAAM,CAAC,MAAM,CAAC,YAAY,KAAK,MAAM,CAAC;AAC5D,MAAM,UAAU,GAAG;IACjB,MAAM,EAAE,qFAAqF;IAC7F,IAAI,EAAE,6BAA6B;CAC3B,CAAC;AAEX,MAAM,SAAS,CAAC;IACd,IAAI,EAAE,qBAAqB;IAC3B,KAAK,EAAE,qBAAqB;IAC5B;;;;OAIG;IACH,WAAW,EAAE,WAAW;IACxB,KAAK,EAAE;QACL,sBAAsB;QACtB,oBAAoB;QACpB,sBAAsB;QACtB,0BAA0B;QAC1B,oBAAoB;QACpB,uBAAuB;QACvB,aAAa,CAAC,CAAC,CAAC,yBAAyB,CAAC,CAAC,CAAC,YAAY,CAAC,yBAAyB,EAAE,UAAU,CAAC;QAC/F,aAAa,CAAC,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,YAAY,CAAC,sBAAsB,EAAE,UAAU,CAAC;KAC1F;IACD,SAAS,EAAE,CAAC,uBAAuB,CAAC;IACpC,OAAO,EAAE,EAAE;IACX,YAAY,EAAE;;;;iMAIiL;IAC/L,OAAO,EAAE,EAAE,WAAW,EAAE,KAAK,EAAE;IAC/B,KAAK,CAAC,IAAI;QACR,4BAA4B,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACxD,uBAAuB,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACnD,uBAAuB,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACnD,SAAS,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACzB,CAAC;CACF,CAAC,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AACA;;;GAGG;AAEH,OAAO,EAAE,SAAS,EAAE,YAAY,EAAE,MAAM,wBAAwB,CAAC;AACjE,OAAO,EAAE,MAAM,EAAE,MAAM,+BAA+B,CAAC;AACvD,OAAO,EAAE,uBAAuB,EAAE,MAAM,iEAAiE,CAAC;AAC1G,OAAO,EAAE,oBAAoB,EAAE,MAAM,+DAA+D,CAAC;AACrG,OAAO,EAAE,yBAAyB,EAAE,MAAM,oEAAoE,CAAC;AAC/G,OAAO,EAAE,sBAAsB,EAAE,MAAM,iEAAiE,CAAC;AACzG,OAAO,EAAE,uBAAuB,EAAE,MAAM,kEAAkE,CAAC;AAC3G,OAAO,EAAE,sBAAsB,EAAE,MAAM,kEAAkE,CAAC;AAC1G,OAAO,EAAE,0BAA0B,EAAE,MAAM,sEAAsE,CAAC;AAClH,OAAO,EAAE,oBAAoB,EAAE,MAAM,+DAA+D,CAAC;AACrG,OAAO,EAAE,sBAAsB,EAAE,MAAM,iEAAiE,CAAC;AACzG,OAAO,EAAE,SAAS,EAAE,MAAM,+BAA+B,CAAC;AAC1D,OAAO,EAAE,uBAAuB,EAAE,MAAM,mDAAmD,CAAC;AAC5F,OAAO,EAAE,4BAA4B,EAAE,MAAM,6DAA6D,CAAC;AAC3G,OAAO,EAAE,uBAAuB,EAAE,MAAM,mDAAmD,CAAC;AAE5F;;;;;;;GAOG;AACH,MAAM,aAAa,GAAG,MAAM,CAAC,MAAM,CAAC,YAAY,KAAK,MAAM,CAAC;AAC5D,MAAM,UAAU,GAAG;IACjB,MAAM,EAAE,qFAAqF;IAC7F,IAAI,EAAE,6BAA6B;CAC3B,CAAC;AAEX,MAAM,SAAS,CAAC;IACd,IAAI,EAAE,qBAAqB;IAC3B,KAAK,EAAE,qBAAqB;IAC5B;;;;OAIG;IACH,WAAW,EAAE,WAAW;IACxB,KAAK,EAAE;QACL,sBAAsB;QACtB,oBAAoB;QACpB,sBAAsB;QACtB,0BAA0B;QAC1B,oBAAoB;QACpB,uBAAuB;QACvB,aAAa,CAAC,CAAC,CAAC,yBAAyB,CAAC,CAAC,CAAC,YAAY,CAAC,yBAAyB,EAAE,UAAU,CAAC;QAC/F,aAAa,CAAC,CAAC,CAAC,sBAAsB,CAAC,CAAC,CAAC,YAAY,CAAC,sBAAsB,EAAE,UAAU,CAAC;KAC1F;IACD,SAAS,EAAE,CAAC,uBAAuB,CAAC;IACpC,OAAO,EAAE,EAAE;IACX,YAAY,EAAE;;;;;iMAKiL;IAC/L,OAAO,EAAE,EAAE,WAAW,EAAE,KAAK,EAAE;IAC/B,KAAK,CAAC,IAAI;QACR,4BAA4B,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACxD,uBAAuB,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACnD,uBAAuB,CAAC,IAAI,CAAC,MAAM,EAAE,IAAI,CAAC,OAAO,CAAC,CAAC;QACnD,SAAS,CAAC,IAAI,CAAC,MAAM,CAAC,CAAC;IACzB,CAAC;CACF,CAAC,CAAC"}

package/dist/mcp-server/resources/definitions/eurostat-dataset.resource.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"eurostat-dataset.resource.d.ts","sourceRoot":"","sources":["../../../../src/mcp-server/resources/definitions/eurostat-dataset.resource.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAY,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAGrD,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;6BAyElC,CAAC"}
+{"version":3,"file":"eurostat-dataset.resource.d.ts","sourceRoot":"","sources":["../../../../src/mcp-server/resources/definitions/eurostat-dataset.resource.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAY,CAAC,EAAE,MAAM,wBAAwB,CAAC;AAGrD,eAAO,MAAM,uBAAuB;;;;;;;;;;;;;;;;;;;;;6BA2ElC,CAAC"}

package/dist/mcp-server/resources/definitions/eurostat-dataset.resource.js

@@ -6,10 +6,12 @@ import { resource, z } from '@cyanheads/mcp-ts-core';
 import { getEurostatDataService } from '../../../services/eurostat-data/eurostat-data-service.js';
 export const eurostatDatasetResource = resource('eurostat://dataset/{dataset_code}', {
     name: 'eurostat-dataset-info',
-    description: 'Dataset metadata for a Eurostat dataset — dimensions, time range, observation count, and last-updated date. Equivalent to eurostat_get_dataset_info but accessible as a resource URI for cache-injectable context.',
+    description: 'Dataset metadata for a Eurostat dataset — dimensions, time range, observation count, and last-updated date. Equivalent to eurostat_get_dataset_info but accessible as a resource URI for cache-injectable context. A DS-* code (detailed trade and PRODCOM) is read from the Comext dissemination host, which reports no time range or observation count.',
     mimeType: 'application/json',
     params: z.object({
-        dataset_code: z.string().describe('Dataset code (e.g., "nama_10_gdp").'),
+        dataset_code: z
+            .string()
+            .describe('Dataset code (e.g., "nama_10_gdp", or "DS-045409" for a Comext collection).'),
     }),
     output: z.object({
         code: z.string().describe('Dataset code.'),

package/dist/mcp-server/resources/definitions/eurostat-dataset.resource.js.map

@@ -1 +1 @@
-{"version":3,"file":"eurostat-dataset.resource.js","sourceRoot":"","sources":["../../../../src/mcp-server/resources/definitions/eurostat-dataset.resource.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,QAAQ,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AACrD,OAAO,EAAE,sBAAsB,EAAE,MAAM,mDAAmD,CAAC;AAE3F,MAAM,CAAC,MAAM,uBAAuB,GAAG,QAAQ,CAAC,mCAAmC,EAAE;IACnF,IAAI,EAAE,uBAAuB;IAC7B,WAAW,EACT,oNAAoN;IACtN,QAAQ,EAAE,kBAAkB;IAC5B,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC;QACf,YAAY,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,qCAAqC,CAAC;KACzE,CAAC;IACF,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC;QACf,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,eAAe,CAAC;QAC1C,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,+BAA+B,CAAC;QAC3D,UAAU,EAAE,CAAC;aACV,KAAK,CACJ,CAAC;aACE,MAAM,CAAC;YACN,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,iBAAiB,CAAC;YAC5C,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,iBAAiB,CAAC;YAC7C,WAAW,EAAE,CAAC;iBACX,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CACP,gLAAgL,CACjL;YACH,YAAY,EAAE,CAAC;iBACZ,KAAK,CACJ,CAAC;iBACE,MAAM,CAAC;gBACN,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,aAAa,CAAC;gBACxC,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC;aAC3C,CAAC;iBACD,QAAQ,CAAC,wCAAwC,CAAC,CACtD;iBACA,QAAQ,EAAE;iBACV,QAAQ,CACP,wIAAwI,CACzI;SACJ,CAAC;aACD,QAAQ,CAAC,4CAA4C,CAAC,CAC1D;aACA,QAAQ,CAAC,qBAAqB,CAAC;QAClC,SAAS,EAAE,CAAC;aACT,MAAM,CAAC;YACN,KAAK,EAAE,CAAC;iBACL,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CAAC,sEAAsE,CAAC;YACnF,GAAG,EAAE,CAAC;iBACH,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CAAC,yEAAyE,CAAC;SACvF,CAAC;aACD,QAAQ,CACP,gIAAgI,CACjI;QACH,QAAQ,EAAE,CAAC;aACR,MAAM,EAAE;aACR,QAAQ,EAAE;aACV,QAAQ,CACP,iHAAiH,CAClH;QACH,WAAW,EAAE,CAAC;aACX,MAAM,EAAE;aACR,QAAQ,EAAE;aACV,QAAQ,CACP,mFAAmF,CACpF;QACH,WAAW,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,6CAA6C,CAAC;KAC3F,CAAC;IAEF,OAAO,CAAC,MAAM,EAAE,GAAG;QACjB,MAAM,GAAG,GAAG,sBAAsB,EAAE,CAAC;QACrC,OAAO,GAAG,CAAC,cAAc,CAAC,MAAM,CAAC,YAAY,EAAE,GAAG,CAAC,CAAC;IACtD,CAAC;CACF,CAAC,CAAC"}
+{"version":3,"file":"eurostat-dataset.resource.js","sourceRoot":"","sources":["../../../../src/mcp-server/resources/definitions/eurostat-dataset.resource.ts"],"names":[],"mappings":"AAAA;;;GAGG;AAEH,OAAO,EAAE,QAAQ,EAAE,CAAC,EAAE,MAAM,wBAAwB,CAAC;AACrD,OAAO,EAAE,sBAAsB,EAAE,MAAM,mDAAmD,CAAC;AAE3F,MAAM,CAAC,MAAM,uBAAuB,GAAG,QAAQ,CAAC,mCAAmC,EAAE;IACnF,IAAI,EAAE,uBAAuB;IAC7B,WAAW,EACT,2VAA2V;IAC7V,QAAQ,EAAE,kBAAkB;IAC5B,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC;QACf,YAAY,EAAE,CAAC;aACZ,MAAM,EAAE;aACR,QAAQ,CAAC,6EAA6E,CAAC;KAC3F,CAAC;IACF,MAAM,EAAE,CAAC,CAAC,MAAM,CAAC;QACf,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,eAAe,CAAC;QAC1C,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,+BAA+B,CAAC;QAC3D,UAAU,EAAE,CAAC;aACV,KAAK,CACJ,CAAC;aACE,MAAM,CAAC;YACN,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,iBAAiB,CAAC;YAC5C,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,iBAAiB,CAAC;YAC7C,WAAW,EAAE,CAAC;iBACX,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CACP,gLAAgL,CACjL;YACH,YAAY,EAAE,CAAC;iBACZ,KAAK,CACJ,CAAC;iBACE,MAAM,CAAC;gBACN,IAAI,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,aAAa,CAAC;gBACxC,KAAK,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,CAAC,cAAc,CAAC;aAC3C,CAAC;iBACD,QAAQ,CAAC,wCAAwC,CAAC,CACtD;iBACA,QAAQ,EAAE;iBACV,QAAQ,CACP,wIAAwI,CACzI;SACJ,CAAC;aACD,QAAQ,CAAC,4CAA4C,CAAC,CAC1D;aACA,QAAQ,CAAC,qBAAqB,CAAC;QAClC,SAAS,EAAE,CAAC;aACT,MAAM,CAAC;YACN,KAAK,EAAE,CAAC;iBACL,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CAAC,sEAAsE,CAAC;YACnF,GAAG,EAAE,CAAC;iBACH,MAAM,EAAE;iBACR,QAAQ,EAAE;iBACV,QAAQ,CAAC,yEAAyE,CAAC;SACvF,CAAC;aACD,QAAQ,CACP,gIAAgI,CACjI;QACH,QAAQ,EAAE,CAAC;aACR,MAAM,EAAE;aACR,QAAQ,EAAE;aACV,QAAQ,CACP,iHAAiH,CAClH;QACH,WAAW,EAAE,CAAC;aACX,MAAM,EAAE;aACR,QAAQ,EAAE;aACV,QAAQ,CACP,mFAAmF,CACpF;QACH,WAAW,EAAE,CAAC,CAAC,MAAM,EAAE,CAAC,QAAQ,EAAE,CAAC,QAAQ,CAAC,6CAA6C,CAAC;KAC3F,CAAC;IAEF,OAAO,CAAC,MAAM,EAAE,GAAG;QACjB,MAAM,GAAG,GAAG,sBAAsB,EAAE,CAAC;QACrC,OAAO,GAAG,CAAC,cAAc,CAAC,MAAM,CAAC,YAAY,EAAE,GAAG,CAAC,CAAC;IACtD,CAAC;CACF,CAAC,CAAC"}

package/dist/mcp-server/tools/definitions/eurostat-browse-themes.tool.js

@@ -7,7 +7,7 @@ import { JsonRpcErrorCode } from '@cyanheads/mcp-ts-core/errors';
 import { getEurostatCatalogueService } from '../../../services/eurostat-catalogue/eurostat-catalogue-service.js';
 export const eurostatBrowseThemes = tool('eurostat_browse_themes', {
     title: 'Browse Eurostat Theme Hierarchy',
-    description: 'Navigate the Eurostat theme tree. Without theme_code returns the top-level theme folders (Economy, Population, Transport, etc.) — the practical starting points. With a theme_code returns its immediate children: subtheme folders and datasets in that branch. Use this for structured discovery when you know the domain but not the dataset code, or to drill down from a broad topic to a specific dataset. Pair with eurostat_search_datasets for keyword-based discovery.',
+    description: 'Navigate the Eurostat theme tree. Without theme_code returns the top-level theme folders (Economy, Population, Transport, etc.) — the practical starting points. With a theme_code returns its immediate children: subtheme folders and datasets in that branch. Use this for structured discovery when you know the domain but not the dataset code, or to drill down from a broad topic to a specific dataset. Pair with eurostat_search_datasets for keyword-based discovery. The tree is the dissemination table of contents plus the Comext host\'s DS-* collections: detailed trade under ext_go_detail (inside ext_go, "International trade in goods") and PRODCOM under prom (inside icts, "Industry, trade and services"). A collection on neither, such as the legacy PRODCOM DS-056120, is not disseminated and appears nowhere in the tree.',
     annotations: { readOnlyHint: true, idempotentHint: true, openWorldHint: true },
     input: z.object({
         theme_code: z