FreightUtils MCP Server

ADR LQ / EQ Exemption Check

adr_lq_eq_check

Read-onlyIdempotent

Check whether dangerous goods qualify for ADR Limited Quantity (LQ, ADR 3.4) or Excepted Quantity (EQ, ADR 3.5) relief. LQ compares each item's per-inner-packaging quantity against that substance's LQ maximum; EQ resolves the substance's E-code (E0-E5) and checks the per-inner limit, plus the per-outer limit when inner_packaging_qty is given.

Provide mode ("lq" or "eq") and 1-20 items, each with un_number, quantity and unit — ml or L for liquids, g or kg for solids; quantity is per INNER packaging, not the whole load.

Unit families: column (7a) states the limit in ONE dimension — a mass for some entries, a volume for others — and ADR supplies no density, so a mass quantity against a volume limit (or the reverse) CANNOT be compared. Those items return status 'inconclusive' with the dimension named, never a pass or a fail, and a batch holding any inconclusive item never reads overall_status 'qualifies'. Send the quantity in the unit given by lq_limit_unit to get a verdict. Multi-variant UNs: a UN number with more than one ADR Table A row (packing group / concentration variant — e.g. UN 1789 PG II LQ 1 L vs PG III LQ 5 L) needs packing_group (I|II|III) or variant_index (from adr_lookup) on that item to pin one row. A packing_group that still leaves several rows is enough when those rows agree on class, column (7a), column (7b) and scope (UN 1790 PG I: two concentration bands, both LQ 0 / E0) — the item is answered with equivalent_variants + variant_note naming the rows it holds for; only when the rows DISAGREE does it still ask for variant_index, and candidates[] then lists only that packing group's rows. With no disambiguator at all: a single-item call, or a batch where EVERY item is ambiguous, returns blocking_errors[AMBIGUOUS_UN_VARIANT] + human_review_required + candidates[] (each candidate's item_index, un_number, variant_index, packing_group, proper_shipping_name, limited_quantity, excepted_quantity) and NO verdict; a MIXED batch withholds only the ambiguous item (status 'withheld', withheld true, row fields null) while the other items are answered, overall_status never reads 'qualifies' while an item is withheld, summary carries withheld, and the envelope carries human_review_required + candidates[] plus one AMBIGUOUS_UN_VARIANT warning per withheld item. Never a silently checked packing group. Single-row UNs are unchanged.

Behavior: deterministic reference check; each item gets a status and reason (an LQ value of "0" or code E0 means the relief is not permitted for that substance), with overall_status and summary counts across the batch. Table A rows listed "NOT SUBJECT TO ADR" (e.g. UN 1845 dry ice) get item status not_subject — outside ADR scope, neither a pass nor a fail — and an all-not-subject batch returns overall_status not_applicable; "CARRIAGE PROHIBITED" rows are not_permitted with the prohibition stated in reason. Fields are checked by name: a field the tool does not read is refused with a tool error naming it and listing the accepted ones, never ignored. Rate-limited: a limit error carries reset_at, the UTC time the allowance resets.

Returns: mode, overall_status (qualifies | does_not_qualify | partial | not_applicable | inconclusive), items[] (un_number, variant_index, substance, class, packing_group, lq_limit or eq_code, quantity_entered, status — within_limit | exceeds_limit | not_permitted | not_subject | inconclusive | withheld — reason, scope flags where applicable, withheld + ambiguity_reason on a withheld item, and equivalent_variants + variant_note when a packing group resolved by equivalence), summary {total_items, qualifying, exceeding, not_permitted, not_subject?, inconclusive?, withheld?}, the ADR chapter references, and human_review_required + candidates[] when any item is withheld — all under result — or, when every item is ambiguous, human_review_required + candidates[] with blocking_errors, plus confidence, _source and citation (the FreightUtils v1 response envelope).

Limitations: a quantity-threshold check only — LQ/EQ relief also requires packaging, marking and documentation conformity that this tool does not assess; not legal advice, verify against the current UNECE ADR text.

Related: adr_lookup (the per-substance LQ/EQ values + variant_index), adr_exemption_calculator (the 1.1.3.6 load-points route instead).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	Yes	Check mode: 'lq' (Limited Quantity, ADR 3.4) or 'eq' (Excepted Quantity, ADR 3.5)
`items`	Yes	Items to check (1–20 per call).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`result`	Yes
`_source`	Yes
`citation`	Yes
`validity`	No
`warnings`	No
`confidence`	Yes
`blocking_errors`	No
`envelope_version`	Yes
`normalized_input`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 8, 2026

changedInput schema / properties / items / items / properties / un_number / description

Previous value: -"UN number — 4 digits, optionally \"UN\"-prefixed; explosives keep the leading zero. Examples: \"1203\", \"UN1263\", \"0004\"."New value: +"UN number — 4 digits, optionally \"UN\"-prefixed; explosives keep the leading zero. Examples: \"1203\", \"UN1263\", \"UN 1263\", \"0004\"."

changedInput schema / properties / items / items / properties / un_number / pattern
```
Previous value: -"^(UN)?\\d{4}$"New value: +"^\\s*(?:UN\\s*)?\\d{4}\\s*$"
```

Changed1 schema field changedOct 7, 2026
- addedInput schema / properties / items / items / properties / quantity / maximum
```
Added value: +1000000000
```
Changed2 schema fields changedOct 6, 2026
- addedInput schema / additionalProperties
```
Added value: +false
```
- addedInput schema / properties / items / items / additionalProperties
```
Added value: +false
```
Changed5 schema fields changedAug 11, 2026
- addedOutput schema / properties / _source / properties / authority_current_edition
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / _source / properties / checked_at
```
Added value: +{
+  "type": "string"
+}
```
- addedOutput schema / properties / _source / properties / dataset_edition
```
Added value: +{
+  "type": "string"
+}
```
- removedOutput schema / properties / envelope_version / const
```
Removed value: -"1"
```
- addedOutput schema / properties / envelope_version / enum
```
Added value: +[
+  "1",
+  "1.1"
+]
```

Changed2 schema fields changedJul 24, 2026

addedInput schema / properties / items / items / properties / packing_group

Added value: +{
+  "description": "Packing group (I, II or III) — only needed to disambiguate a UN with more than one ADR Table A row (e.g. UN 1789: PG II LQ 1 L vs PG III LQ 5 L). Ignored for single-row UNs.",
+  "enum": [
+    "I",
+    "II",
+    "III"
+  ],
+  "type": "string"
+}

addedInput schema / properties / items / items / properties / variant_index

Added value: +{
+  "description": "ADR Table A variant index (as returned by adr_lookup) — pins one row when a UN has several variants that share a packing group (e.g. concentration bands). Ignored for single-row UNs.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}

Changed1 schema field changedJul 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "_source": {
+      "additionalProperties": false,
+      "properties": {
+        "checked": {
+          "type": "string"
+        },
+        "name": {
+          "type": "string"
+        },
+        "provenance_status": {
+          "enum": [
+            "verified",
+            "pending-verification",
+            "computed",
+            "live"
+          ],
+          "type": "string"
+        },
+        "source_url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "name",
+        "checked",
+        "provenance_status"
+      ],
+      "type": "object"
+    },
+    "blocking_errors": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "code": {
+            "type": "string"
+          },
+          "message": {
+            "type": "string"
+          },
+          "recovery": {
+            "additionalProperties": false,
+            "properties": {
+              "action": {
+                "type": "string"
+              },
+              "params": {
+                "additionalProperties": {},
+                "propertyNames": {
+                  "type": "string"
+                },
+                "type": "object"
+              },
+              "tool": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "action"
+            ],
+            "type": "object"
+          }
+        },
+        "required": [
+          "code",
+          "message",
+          "recovery"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "citation": {
+      "additionalProperties": false,
+      "properties": {
+        "qualifier": {
+          "type": "string"
+        },
+        "text": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "text"
+      ],
+      "type": "object"
+    },
+    "confidence": {
+      "additionalProperties": false,
+      "properties": {
+        "basis": {
+          "enum": [
+            "deterministic",
+            "provenance",
+            "match_quality",
+            "freshness"
+          ],
+          "type": "string"
+        },
+        "level": {
+          "enum": [
+            "high",
+            "medium",
+            "low"
+          ],
+          "type": "string"
+        },
+        "score": {
+          "maximum": 1,
+          "minimum": 0,
+          "type": "number"
+        }
+      },
+      "required": [
+        "level",
+        "basis"
+      ],
+      "type": "object"
+    },
+    "envelope_version": {
+      "const": "1",
+      "type": "string"
+    },
+    "normalized_input": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "ok": {
+      "type": "boolean"
+    },
+    "result": {
+      "additionalProperties": {},
+      "propertyNames": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "validity": {
+      "additionalProperties": false,
+      "properties": {
+        "as_of": {
+          "type": "string"
+        },
+        "effective_from": {
+          "type": "string"
+        },
+        "effective_to": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        }
+      },
+      "required": [
+        "as_of"
+      ],
+      "type": "object"
+    },
+    "warnings": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "code": {
+            "type": "string"
+          },
+          "details": {
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          },
+          "message": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "code",
+          "message"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "envelope_version",
+    "ok",
+    "result",
+    "confidence",
+    "_source",
+    "citation"
+  ],
+  "type": "object"
+}

Changed9 schema fields changedJun 17, 2026

changedInput schema / properties / items / description

Previous value: -"Items to check"New value: +"Items to check (1–20 per call)."

changedInput schema / properties / items / items / properties / inner_packaging_qty / description

Previous value: -"Number of inner packagings (EQ mode only)"New value: +"EQ mode only: number of inner packagings per outer package, for the per-outer limit check. Default 1. Example: 10."

changedInput schema / properties / items / items / properties / quantity / description

Previous value: -"Quantity of substance"New value: +"Quantity per inner packaging, expressed in the chosen unit. Example: 0.5."

changedInput schema / properties / items / items / properties / un_number / description

Previous value: -"4-digit UN number"New value: +"UN number — 4 digits, optionally \"UN\"-prefixed; explosives keep the leading zero. Examples: \"1203\", \"UN1263\", \"0004\"."

addedInput schema / properties / items / items / properties / un_number / pattern
```
Added value: +"^(UN)?\\d{4}$"
```

changedInput schema / properties / items / items / properties / unit / description

Previous value: -"Unit of measurement"New value: +"Unit for the quantity: \"ml\" or \"L\" for liquids, \"g\" or \"kg\" for solids."

addedInput schema / properties / items / maxItems
```
Added value: +20
```
addedInput schema / properties / items / minItems
```
Added value: +1
```

changedInput schema / properties / mode / description

Previous value: -"Check mode: lq (Limited Quantity) or eq (Excepted Quantity)"New value: +"Check mode: 'lq' (Limited Quantity, ADR 3.4) or 'eq' (Excepted Quantity, ADR 3.5)"

First observedApr 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantial extra context: inconclusive handling for dimension mismatches, withheld/ambiguity semantics, not_subject vs not_permitted, field-name rejection, and rate-limit reset_at. This is well beyond what structured fields disclose.

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

Conciseness4/5

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

Purpose is front-loaded and every section addresses a genuine edge case, but the prose is dense with long compound sentences (especially the variant/ambiguity passage) that could be tightened. Size is justified by the tool's complexity, so only minor trimming is warranted.

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

Completeness5/5

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

An output schema exists, yet the description still maps statuses, summary counts, envelope fields, and limitations clearly enough for an agent to interpret results. For a many-edge-case regulatory checker, nothing needed to call or read it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds real meaning: quantity is per inner packaging not per load, the unit-dimension mismatch consequence, when packing_group suffices vs when variant_index is needed, and the EQ per-outer limit. It goes meaningfully beyond the schema text.

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

Purpose5/5

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

States a specific verb+resource (check ADR LQ/EQ relief qualification) and immediately names the regulatory basis (ADR 3.4, 3.5). It distinguishes itself from siblings by routing to adr_lookup for values and adr_exemption_calculator for the 1.1.3.6 route.

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

Usage Guidelines5/5

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

Explicitly says which mode to provide and how to supply items, and names the alternative exemption route (adr_exemption_calculator) so the agent can pick the right tool. The 'Related' block plus inline cross-references make the when/when-not choice clear.

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

All FreightUtils MCP Server tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.