EU Trade Explorer
Deskriptive und analytische Statistiken über den EU-Handel und die Industrieproduktion
Dokumentation
EU Trade Explorer -- MCP bridge
EU Trade Explorer MCP bridge for Eurostat Comext customs trade and PRODCOM industrial production.
Access
Tool calls and resource reads use OAuth 2.1 or a personal API key with a free account. Discovery and listings are public. See chatbots and API access and data sources.
Tool discovery
The initial listing pins the common product-resolution, coverage, overview and documentation tools. For every other analysis, call search_tools with a natural-language description. It returns at most three matching tools with their complete input schemas. Execute a match through call_tool with name set to the returned tool name and arguments set to that tool's keyword arguments. Existing clients may still call every canonical tool name directly.
Search results omit bulky output schemas and carry a contractUrl instead. The complete MCP contract preserves every input and output schema.
Tool results
Typed tools return structured content in a stable {"result": ...} envelope. Report-section tools put the section there; get_full_report puts the shared query and all five sections there.
Documentation
Call get_documentation or read eu-trade://docs/<topic> for a short guide and website links. Topics: query-model, customs-codes, prodcom, methodology, reporting.
Connecting
- Transport: Streamable HTTP, at https://mcp.tradedashboard.eu/mcp
- Listing tools and resources needs no credential; calling a tool or reading a resource requires an account.
- An unauthenticated call is answered 401 with auto-discovery metadata (OAuth 2.1); a normal MCP client follows that discovery chain and the login/consent flow automatically -- registration is free and currently unlimited.
- The response is a single JSON-RPC object,
{'jsonrpc': '2.0', 'id': 1, 'result': {...}}; the tool's own return value is underresult.structuredContent(and as text underresult.content[0].text). Any tool can be called this way --params.argumentsis just that tool's keyword arguments (query,compact, ...) as a JSON object.
Core tools (13)
- get_documentation -- Read one complete MCP guide:
query-model(access, shared query fields, pieces and baskets),customs-codes(segments, residuals and historical selections),prodcom(production mappings, suppression and availability),methodology(indicator formulas and interpretation), orreporting(short/long workflows and dashboard navigation). The same canonical text is available aseu-trade://docs/<topic>resources. - guidelines_for_a_short_report -- Read this first for a quick report. Returns the short-report workflow: resolve a product code, then call
get_full_reportfor the five most important report sections in one shot -- enough for a quick, simple report. Also covers access, the sharedqueryobject and thecompactoption. - guidelines_for_a_long_report -- Read this first for an in-depth report. Returns the long-report workflow: which of the 35+ tools to combine per angle (partners, concentration, volatility & shocks, autonomy), the dashboard menu/tab structure for pointing readers at views, and the methodological notes needed to interpret and cite figures correctly. Call this before guessing at tool use.
- get_countries -- Reference data for reporters/partners: selectable EU/Euro-area/Member States, named partner presets, predefined reporter/partner groups, and per-language country-name translations. Use this to find valid values for the
reporter,partner_set,partnersandgroup_reportersfields used throughout the other tools'queryargument. - get_data_range -- Return the period coverage (
data_min/data_max, 'YYYY-MM') actually cached for the given customs code(s) -- use before pickingperiod_start/period_endso you don't request an empty window. - get_overview -- Headline figures: total import/export quantities, values and weighted-average prices per period, the trade balance, and a top-partner breakdown. The best first call for any new customs-code/reporter slice. The figures sit under
total/partners/balance, each panel carrying its ownperiodsaxis; the metadata (units, residual share, selection notes) is inheader. - get_partner_detail -- Per-partner import/export breakdown. For each flow, the top-N trading partners ranked both by quantity and by value (so you can compare volume-based vs. value-based rankings), each with its own quantity, value and price time series, plus an optional 'Other' bucket.
- get_reporter_detail -- Per-EU-Member-State import/export breakdown -- the reporter-side counterpart of
get_partner_detail. Top-N Member States (by quantity and by value) with their quantity, value and price series. Aggregate reporters (EU, Euro area, groups) are excluded from the ranking. - get_concentration -- Herfindahl-Hirschman Index (HHI) of trade concentration across partners or Member States, per period (0 = perfectly spread, 10000 = one entity holds the whole market), plus the top-8-by-value share breakdown (rest bundled as 'Others'). Higher HHI = more dependent on a handful of counterparties.
- get_volatility -- Coefficient-of-variation (CV = stdev / mean) volatility per partner/reporter x customs-code pair, over inactive-period-excluded history. Higher CV = the flow swings more relative to its typical level. Returns per-entity CV bars (with drill-down series) and, unless include_heatmap=false, an entity x sub-code CV heatmap.
- get_net_import_reliance -- Net Import Reliance (NIR) = (Imports - Exports) / Apparent consumption, annual, joining PRODCOM production with Comext trade. E.g. 40% means 40% of EU consumption is met by imports; negative means the EU is a net exporter. Returns the NIR % series, its supply/disposition components, sibling-category/per-code comparisons, the resolved PRODCOM codes and availability notes (CN-to-PRODCOM mapping is not always 1:1; see the
comparison.prodcom.notes/comparison.prodcom.unavailability_typefields in the response). Usequery.prodcom_codeto pin a specific mapping. - resolve_product_code -- Resolve a free-text query or CN code(s) into validated customs code(s) with descriptions -- the recommended first step before using a code as
customs_codein any other tool'squery. Saves the search -> validate -> (optional) subtree round-trip: a bare keyword runs a search, a single code (or comma-separated list) is validated and described directly. Tip: Comext/CN nomenclature is frequently coarser than a colloquial product name (e.g. there is no code for "glass jars" alone -- only heading 7010, which bundles jars with bottles, flasks and closures). Checkhas_subcodesand, if useful, setinclude_children=trueto see whether a finer sub-code is actually a better match before committing to one code for a whole report. Returns{mode, query, data}:datais the typed validation or search response. A single-code validation also carriessubtreewhen requested. - get_full_report -- Fetch every report section (scope, overview, market structure, volatility, autonomy) for one shared
query(labels inquery.lang) in a single call, instead of callingget_customs_code_profile/get_market_summary/get_market_structure_summary/get_volatility_summary/get_autonomy_summaryseparately yourself. Guarantees all five sections describe the exact same customs-code/reporter/partner/period slice -- five separate calls have no such guarantee, since nothing stopsqueryfrom being re-typed slightly differently across them, or one of the five simply being forgotten.query's own field defaults (reporter='European Union',partner_set='non-EU countries',period_start='2015-01',frequency='quarter',remove_outliers=true, ...) are exactly the sensible defaults for a first-cut report; override any of them for a different slice -- e.g. a specific Member State, a custom partner group, a narrower period. Returns{"result": {"query": {...}, "sections": {<name>: {narrative_facts, chart_data, links, available, reason}, ...}}}for<name>incustoms_code_profile,market_summary,market_structure,volatility,autonomy.linksmaps eachnarrative_factskey to a ready-madehttps://tradedashboard.eu/...URL for that same fact -- never construct one of these yourself; use the one already provided.
Advanced tools (25)
- get_chapters -- List all top-level Combined Nomenclature chapters (2-digit codes). Bootstraps browsing the nomenclature top-down; drill into a chapter with
get_subtree. - get_subtree -- Return the Combined Nomenclature sub-tree rooted at
customs_code(its sub-codes, and their sub-codes, ...), each with acustoms_codeand atextdescription. Use this to see whether a heading you're about to use (e.g. asquery.customs_codeelsewhere) is actually a clean match, or bundles several distinct sub-codes together. - validate_customs_code -- Validate and describe one or more Combined Nomenclature codes. For a single code, returns the full hierarchy of description levels (
levels), the resolvedcustoms_code_label, andhas_subcodes. For a comma-separated list, returns{"results": [...]}with one entry per code (each either a success dict or a{"customs_code", "error"}pair). - search_customs_codes -- Keyword/code search over the Combined Nomenclature (or PRODCOM). Returns ranked
{code, label, path}candidates. Preferresolve_product_codefor a one-call keyword-or-code helper; use this directly if you specifically want the raw ranked candidate list. - get_reporter_benchmark -- Every EU reporter ranked by value for one year -- the country-view counterpart of
get_reporter_detail. Returns a single-year snapshot (every real EU Member State's quantity, value and price per flow, ranked by value) plus a benchmark price time series: the weighted average across whichever reportersquery.reporterresolves to (the whole EU by default, or narrower whenquery.reporteris itself an aggregate -- euro area, a named group, or an ad hoc custom group), the cross-reporter min/max envelope, and the selected reporter's own line whenquery.reporteris a single real Member State. Use it to answer "how does this country -- or reporter group -- compare to every other reporter?". - get_map_data -- Choropleth-ready aggregates: per-period totals (quantity, value, price) for imports and exports, keyed by GISCO country code on both the reporter and partner sides.
- get_top_entities -- Just the ordered list of top entities for a slice -- no time series. A lightweight helper for populating entity pickers or quickly checking who the top partners/reporters are without pulling full series.
- get_production_series -- EU27 and per-country PRODCOM production series: EU quantity, EU production unit value, and the same two per reporting country (all DS-059358 reporters, not just EU-27, since production data carries no trade columns). Country-level figures are heavily confidentiality -suppressed; suppressed/absent values come back as null, not zero. Use
query.prodcom_codeto pin a specific PRODCOM mapping when a customs code maps to several. Accepts exactly one customs code; multi-code selections are rejected. - get_subcode_compare -- Sub-code comparison: for a single parent customs code, expands into its sub-codes (or, for a multi-code request, compares the entered codes directly) and returns per-subcode quantity/value/price series for both flows -- so each sub-code plots as its own line instead of being aggregated away. The
breakdownblock is discriminated bystate: 'ok' carries the panels, a leaf code returns 'leaf' and an unexpandable nomenclature 'unavailable', each with amessage. - get_concentration_compare -- Partner-concentration (HHI) compared across sub-codes: one HHI line per sub-code rather than per flow, to see which sub-codes drive a parent code's overall concentration.
- get_concentration_map -- Cross-sectional HHI per country for one year -- the choropleth counterpart of get_concentration. 'partner' entity_level = for every EU member state, HHI of its trade across partners; 'reporter' = for every partner, HHI of its trade across EU member states (subject to the Rotterdam/Antwerp entry-point distortion).
- get_specialisation -- Intra-EU revealed symmetric comparative advantage (RSCA) per Member State -- a Balassa index benchmarked against the EU instead of the world. Runs -1 (under-specialised) to +1 (strongly specialised), value -based and intra-EU only. Treat with caution: intra-EU flows are distorted by the Rotterdam/Antwerp quasi-transit effect.
- get_production_concentration -- How concentrated production of a customs code's goods is across all DS-059358 reporting countries (PRODCOM; EU Member States plus EFTA/candidate/other reporters -- not only the EU-27). HHI of PRODVAL across countries over time, plus each country's production share. Suppressed/absent country figures come back as null, not zero. Use
query.prodcom_codeto pin a specific PRODCOM mapping. Accepts exactly one customs code; multi-code selections are rejected. - get_pattern_shift -- Before/after trade-pattern shift around a split point (
query.midpoint): for each entity, compares average quantity and price before vs. after, and returns scatter points (quantity-change % vs. price-change %) with quadrant labels -- top-right = demand-driven growth, top-left = supply constraint/monopoly risk, bottom-right = dumping/oversupply risk, bottom-left = market contraction. Suggested workflow: omitquery.midpointto receive the default analysis and every valid split point inavailable_midpoints, then set one of those values asquery.midpointhere. An explicit midpoint that cannot form a valid split returns a 422 error frame. - get_supply_shocks -- Detect abnormal collapses in trade volumes ("sudden volume changes"). Flags periods where a partner × customs-code pair's volume drops well below its historical average (>2 sigma by default). Returns ranked shock events per flow, each with timeline phases (baseline, decline, disruption, recovery, ...), magnitude, abnormality score and underlying series.
- get_price_shocks -- Detect sudden price regime shifts ("rapid price changes"), accounting for each flow's usual volatility so naturally volatile flows aren't over-flagged. Returns ranked shock events per flow with timeline phases (price spike/drop, volatile trade, return to baseline, ...), magnitude and series.
- get_trade_intensity -- Trade Intensity (TI) = (Imports + Exports) / (Imports + Production), annual. Near 1 = highly trade-exposed sector; near 0 = predominantly domestic. Used in the Commission's CEEAG methodology for carbon-leakage / State-aid eligibility. Returns the TI series, its components, sibling-category/per-code comparisons, resolved PRODCOM codes and availability notes.
- get_export_propensity -- Export Propensity = Exports / Production, annual: the share of EU production that is exported. Not clamped -- values above 100% are legitimate (re-exports, stock drawdown, scope differences). Returns the export-propensity matrix, a sibling/per-code comparison, resolved PRODCOM codes and availability notes.
- get_subcontracting -- EU27 sub-contracting intensity: the share of sold production that is toll (sub-contracted) manufacturing rather than own-account output. Returns intensity (%) across value/quantity, its component series, per-period data-quality status, resolved PRODCOM codes and availability notes. The own/sub split only exists from 2021 onward. Accepts exactly one customs code; multi-code selections are rejected.
- get_subcontracting_reporters -- Per-country sub-contracting intensity (PRODCOM): for each reporting country, the share of its sold production that is toll manufacturing -- which countries act as processing hubs vs. autonomous producers. Spans all DS-059358 reporters that report the own/sub split; others simply don't appear. Country cells are heavily confidentiality-suppressed (null, not zero, when absent). Accepts exactly one customs code; multi-code selections are rejected.
- get_customs_code_profile -- Report-section helper ("Scope & definitions"): the resolved customs code + label (in
query.lang), a one-sentence caveat when the code bundles several sub-codes (has_subcodes), the data-coverage window actually cached for it, and whether it has a usable PRODCOM mapping (gating the autonomy/vulnerability section). Deliberately thin -- no full CN hierarchy breadcrumb or sibling enumeration. Returns{"result": {narrative_facts, chart_data, links, available, reason}}-- seeget_market_summaryfor the section shape this convention follows across all of this bridge's report-section helpers. - get_market_summary -- Report-section helper ("General overview"): condensed, report-ready digest of how a market has evolved over the chosen window -- one call instead of separately fetching and cross-referencing get_overview + get_reporter_detail + get_concentration + get_net_import_reliance yourself. Set
query.frequency = "year"for a multi-year evolution summary (recommended over the model's default of "quarter"). Every figure reflectsqueryexactly as given -- the same customs-code/reporter/partner_set/period slice a dashboard user would have selected. Nothing here substitutes a different reporter or partner_set (e.g. to contrast intra-EU against extra-EU trade): call this again with a differentquery.partner_setfor that, the same way a dashboard user would switch the sidebar's selector. Returns{"result": {narrative_facts, chart_data, links, available, reason}}.narrative_factscombines, for the flow selected byquery.partner_set: - Headline trade: first/last/min/max/pct_change for export & import value, quantity and price, plus the trade-balance trend. - Partner concentration: first/last/pct_change of the value-based HHI for imports and exports. - Top partners and top EU reporters by value: each one's first/last/pct_change -- i.e. who is gaining or losing share. - Net import reliance: first/last/pct_change of the annual NIR % forquery's ownreporter/partner_set(onlyfrequencyis normalised to "year", since NIR is structurally annual and the upstream API always returns it that way regardless); omitted if the customs code has no PRODCOM mapping.chart_datacarries the full-fidelity headline trade and top-partner/ top-reporter series for charting. - get_market_structure_summary -- Report-section helper ("Market structure"): combines, in priority order, the intra-EU specialisation snapshot (
get_specialisation, already map-ready), partner-concentration detail (get_concentration, keeping the top-8-by-value share breakdown aschart_dataalongside the condensed HHI trend) and, when a PRODCOM mapping exists for the customs code, EU production volumes (get_production_series). These three are independent data sources bundled only because they all describe "market structure" -- the specialisation RSCA is trade-based and has no relation to the PRODCOM production figures; treat them as separate findings, not a single connected story.most_specialised_reporters/least_specialised_reportersare pre-sorted by actual RSCA (highest/ lowest first respectively) -- use them as-is rather than re-deriving a ranking.query.prodcom_codeis passed through untouched -- picking among ambiguous PRODCOM mappings is left to the caller, never guessed here. Returns{"result": {narrative_facts, chart_data, links, available, reason}}. - get_volatility_summary -- Report-section helper ("Volatility & shocks"): the entities analysed are picked by
get_volatility(ranks by trade volume, reports each one's CV) and byget_price_shocks/get_supply_shocksat default parameters (both already scoped to top-value partners viacumulative_share=0.8) -- never re-picked from the shocks themselves. Retries shock detection once with loosened thresholds before concluding "no shocks"; an empty result is itself a reportable finding, not a gap. When shocks are found, the top events by abnormality and their series are the section's findings; when none are found (even after the retry), stability is the finding.get_pattern_shiftis intentionally not part of this bundle -- its before/after quadrant framing is too easily misread; call it directly if you specifically need it. Returns{"result": {narrative_facts, chart_data, links, available, reason}}. - get_autonomy_summary -- Report-section helper ("Autonomy & vulnerability"): net import reliance (
get_net_import_reliance) is always the headline fact/chart. Trade intensity and export propensity (get_trade_intensity/get_export_propensity) are both computed, then a deterministic salience score -- distance from an unremarkable ~50% band, plus the magnitude of its own change -- decides which one leads the narrative; this choice is never left to the caller.trade_intensity_pctis returned fully unit-consistent (first/last/min/max all expressed as a percentage, matchingexport_propensity_pct). Sub-contracting is deliberately not included in this section at all -- it is an unrelated, tiny-base PRODCOM series that only muddied the narrative. Returns{"result": {narrative_facts, chart_data, links, available, reason}}.
On-demand Documentation
query-model--get_documentation(topic="query-model")or MCP resourceeu-trade://docs/query-modelcustoms-codes--get_documentation(topic="customs-codes")or MCP resourceeu-trade://docs/customs-codesprodcom--get_documentation(topic="prodcom")or MCP resourceeu-trade://docs/prodcommethodology--get_documentation(topic="methodology")or MCP resourceeu-trade://docs/methodologyreporting--get_documentation(topic="reporting")or MCP resourceeu-trade://docs/reporting
Docs
- Dashboard & REST API llms.txt -- a different surface, see the note above
- Complete MCP tool contract -- all 38 input/output schemas; search results link here instead of repeating output schemas
- Help