Docs → API reference

AI Infrastructure Equipment Trade (chip-making tools) API v1

Generated from core.contract.describe_ai_infrastructure_equipment_trade_v1() and checked fixture-backed examples. Do not hand-edit the example JSON files.

Capability

• Capability: ai_infrastructure.equipment_trade
• Primitive: query_ai_infrastructure_equipment_trade_v1
• Status: available
• Current source: trade.census.intltrade_equipment_hs
• Source publisher: U.S. Census Bureau
• Snapshot behavior: as_of = latest resolves to an exact snapshot date in every response.

What It Can Answer

• Monthly U.S. import value (USD) of semiconductor-manufacturing equipment — HS-8486 — cited to the source row.
• Equipment imports by country of origin (e.g. Japan, the Netherlands, South Korea) — tool-supply concentration.
• The fab-buildout tooling trend (each country / grouping / the national total as its own monthly series).
• General imports value vs imports-for-consumption value at the same grain.
• Row-level detail records when include_records is true.
• Raw Census response-row evidence for any returned row-level citation.

Represented Facts

• Census International Trade reports the monthly customs value (USD) of U.S. imports of HS-8486 'Machines and apparatus for the manufacture of semiconductor boules/wafers, devices, integrated circuits or flat panel displays' — the chip-MAKING equipment (which includes flat-panel-display machinery), NOT the chips themselves — by country of origin, as general imports and imports-for-consumption value, served verbatim and cited
• Census reports these imports across overlapping country GROUPINGS (ASIA, APEC, EU, OECD, ASEAN, the continents) and an all-countries TOTAL; the groupings overlap each other and the countries, so they are never summed — the served TOTAL is the only national figure

Data Point Contract

• Data point: ai_infrastructure.equipment_trade
• Product spec: blocks/ai_infrastructure_equipment_trade/card.md
• Grain: commodity_country_monthly
• Source basis: trade.census.intltrade_equipment_hs
• Represented fact: Census International Trade reports the monthly customs value (USD) of U.S. IMPORTS of HS-8486 "Machines and apparatus of a kind used solely or principally for the manufacture of semiconductor boules or wafers, semiconductor devices, electronic integrated circuits or flat panel displays" — the chip-MAKING equipment (lithography, deposition, etch, and related tools), which INCLUDES flat-panel-display machinery and is NOT the chips themselves — by country of origin and as Census's own published country GROUPINGS and TOTAL. Served as two value series exactly as Census publishes: general imports value and imports-for-consumption value. Value only. Each row is served verbatim + cited; the country groupings overlap and are never summed.

Does not answer:

• the chips themselves — HS-8486 is the MANUFACTURING EQUIPMENT; integrated-circuit imports are HS-8542 (ai_infrastructure.trade)
• a semiconductor-only reading — the HS-8486 heading ALSO covers flat-panel-display manufacturing machinery; Census does not split them at this level
• tool-type or vendor breakdown — one HS4 heading; no lithography-vs-deposition-vs-etch split, no per-manufacturer (e.g. ASML) series
• summing across country rows — Census's groupings (ASIA, APEC, EU, OECD, ASEAN, Pacific Rim, the continents) OVERLAP each other and the individual countries; the served "TOTAL FOR ALL COUNTRIES" (country_level=total) is the only valid total, never a sum the agent computes
• quantity or unit counts of tools — the measure is customs value (USD) only at this level
• landed / CIF / duty-paid cost — general imports value is customs value; CIF, charges, and calculated duty are separate Census fields not served here
• which U.S. fab, state, county, or operator receives the equipment — country is the country of ORIGIN (Census attribution), not a U.S. destination; this series carries no U.S. geographic anchor
• exports (this block serves IMPORTS only) or trade in non-HS-8486 goods
• finality (recent months are preliminary and revised in later Census releases)

REST Surface

• GET /v1/health
• GET /v1/capabilities
• GET /v1/ai-infrastructure/equipment-trade/schema
• POST /v1/ai-infrastructure/equipment-trade/query
• POST /v1/evidence/source-row

MCP Surface

• list_capabilities_v1
• describe_ai_infrastructure_equipment_trade_v1
• query_ai_infrastructure_equipment_trade_v1
• get_source_evidence_v1

Local MCP Setup

Some MCP clients launch servers from the user's home directory or ignore a configured cwd. Use uv run --directory so the server always starts from the repository project.

{
  "command": "uv",
  "args": [
    "run",
    "--directory",
    "/absolute/path/to/OSINT",
    "python",
    "-m",
    "core.mcp_server"
  ]
}

Leave EXASCALE_PARQUET_BASE / EXASCALE_RAW_BASE unset: the one server hosts every data point's tools, and with no override it resolves each block's promoted snapshots and raw archive from the repository layout. Setting either env var points ALL tools at one directory — a per-block path breaks every other block's tools. They exist only for single-source sandboxes and tests.

Request Schema

Filters:

• as_of
• country
• cty_code
• country_level
• data_month
• data_month_from
• data_month_to
• year

Group by:

• country
• cty_code
• country_level
• data_month
• year

Date range parameters:

• data_month_from
• data_month_to

Controls:

• include_records
• include_evidence
• limit
• order_by
• top_n
• order
• rollup_other

Ranking (how order_by / top_n / order join — order_by ranks groups by a metric, never a group_by dimension; top_n needs both a group_by and an order_by):

{
  "no_ranking": "Omit order_by and top_n to return all groups in group-key order.",
  "order": {
    "default": "desc",
    "valid_values": [
      "desc",
      "asc"
    ]
  },
  "order_by": {
    "accepts": "one of output.metrics",
    "note": "Ranks the groups by a metric (a measure). Not a group_by dimension \u2014 rows already come back grouped by each group_by field.",
    "requires": [
      "group_by"
    ],
    "valid_values": [
      "general_value_usd",
      "consumption_value_usd",
      "source_record_count"
    ]
  },
  "top_n": {
    "note": "Keeps the top N groups by order_by; the rest fold into one (other) remainder (additive metrics sum into it, non-additive ones are nulled) so the result still reconciles to summary.totals.",
    "requires": [
      "group_by",
      "order_by"
    ],
    "type": "positive integer"
  }
}

Output Schema

Aggregate metrics:

• general_value_usd
• consumption_value_usd
• source_record_count

Metric groups:

{
  "consumption_value_usd": [
    "consumption_value_usd"
  ],
  "general_value_usd": [
    "general_value_usd"
  ],
  "records": [
    "source_record_count"
  ]
}

Response summary fields:

• group_count
• totals

Accepted fact policy:

• Query responses contain accepted, gate-passed facts only.
• Gate, monitor, and audit quality signals are internal controls, not agent-facing answer caveats.
• If a source snapshot is not fit to serve, the source must fail closed before it reaches this API.

Metric metadata:

Rollup rules:

• summary.totals.<metric> is the authoritative total for the full matched query.
• Grouped row metrics may be summed only when additive_across_groups is true.
• Do not sum grouped values for these non-additive metrics: general_value_usd, consumption_value_usd.

Detail record fields returned when include_records is true:

• source_id
• sheet_name
• source_record_key
• report_period
• commodity
• commodity_desc
• cty_code
• country
• country_level
• data_month
• year
• general_value_usd
• consumption_value_usd
• source_row_number
• as_of
• raw_file_sha256
• citation

Row-level citation fields:

• source_id
• source_url
• source_file
• sheet
• source_row
• raw_file_sha256
• as_of

Aggregate citation fields:

• source_id
• publisher
• source_url
• source_file
• raw_file_sha256
• as_of
• source_rows_count
• source_rows_sample
• verify
• lineage_filter

Codebooks

The complete machine-readable codebooks are included in capability-schema.json.

Checked Examples

The checked schema output is capability-schema.json.

Agent Workflow

1. Call list_capabilities_v1 and select ai_infrastructure.equipment_trade.
2. Call describe_ai_infrastructure_equipment_trade_v1 to inspect valid filters, groupings, metrics, and citation fields.
3. Call query_ai_infrastructure_equipment_trade_v1 with bounded JSON params.
4. If the answer needs proof, pass a returned row-level citation object to get_source_evidence_v1.
5. Answer with the resolved as_of and relevant citations. Present returned metrics as authoritative for their declared source, snapshot, grain, and aggregation.