Skip to main content
Glama

FreightUtils MCP Server

by io.github.SoapyRED

ADR Dangerous Goods Lookup

adr_lookup
Read-onlyIdempotent

Look up European road dangerous-goods (ADR 2025) reference data for a substance: hazard class, classification code, packing group, labels, special provisions, limited/excepted quantities, transport category, tunnel restriction code and Kemler (hazard identification) number. Covers 2,939 entries across all 9 hazard classes, from UNECE ADR 2025 (ECE/TRANS/352).

Provide exactly ONE of: un_number (exact lookup — returns every packing-group variant of that UN number), search (case-insensitive partial match on the proper shipping name), or hazard_class (all entries in a class or division). un_number is normalised — "1203", "UN1203" and "un 1203" are equivalent, and normalized_input reports the correction; explosives keep their leading zero ("0004").

Behavior: read-only reference lookup; name searches return up to 50 entries, class filters up to 100. An unknown UN number or a search with no hits errors with the API's NOT_FOUND body and a retry hint. 28 Table A rows carry a scope remark instead of a packing group: those return packing_group null plus not_subject_to_adr (with conditions_ref, e.g. "5.5.3" for UN 1845 dry ice) or carriage_prohibited, and table_a_remark preserves the verbatim Table A text. Rate-limited (anonymous use: 25 requests/day per IP): a 429 error body carries retry_after_seconds and a Retry-After header — back off and retry, or call get_subscribe_link for higher limits.

Returns: count and results[] — per entry: un_number, proper_shipping_name, class, classification_code, packing_group, labels, special_provisions, limited_quantity, excepted_quantity, transport_category, tunnel_restriction_code, hazard_identification_number, variant_index/variant_count and, on scope-flagged rows, not_subject_to_adr/carriage_prohibited/conditions_ref/table_a_remark — under result, plus confidence, _source and citation (the FreightUtils v1 response envelope).

Limitations: a factual compilation of the ADR table, not legal or compliance advice; classification remains the consignor's responsibility — verify against the current UNECE ADR text.

Related: adr_lq_eq_check (checks quantities against the LQ/EQ values returned here), adr_exemption_calculator (1.1.3.6 small-load points), consignment_calculator (flags dangerous-goods lines by UN number).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
searchNoCase-insensitive partial match on the proper shipping name (min 2 characters). Example: "acetone".
un_numberNoExact UN number — 4 digits, optionally "UN"-prefixed; explosives keep their leading zero. Examples: "1203", "UN1203", "0004".
hazard_classNoFilter by ADR hazard class and its divisions. Examples: "3" (flammable liquids), "6.1" (toxic), "8" (corrosive), "1.4" (an explosives division).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
okYes
resultYes
_sourceYes
citationYes
validityNo
warningsNo
confidenceYes
blocking_errorsNo
envelope_versionYes
normalized_inputNo

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, and the description adds substantial context: rate limits (25 req/day per IP), 429 retry semantics with retry_after_seconds and Retry-After header, NOT_FOUND error behavior, 50/100 result caps, UN-number normalization with normalized_input reporting, and the 28 scope-flagged rows returning packing_group null plus not_subject_to_adr/carriage_prohibited. No contradiction with annotations.

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

Conciseness5/5

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

The description is long but every sentence earns its place. It is front-loaded with the core purpose, then progresses through lookup modes, behavioral details, return envelope, limitations, and related tools. Clear paragraph structure (Behavior, Returns, Limitations, Related) makes the density navigable for an agent.

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?

Output schema exists, so return values need not be re-explained, yet the description still summarizes the envelope (count, results[], confidence, _source, citation). It covers edge cases (scope-flagged rows, leading-zero explosives), error semantics, rate limiting, and the legal disclaimer. Nothing material is missing for a data-heavy lookup tool with three modes and zero required parameters.

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 the baseline is 3. The description adds genuinely useful semantics beyond the schema: the mutual-exclusion constraint ('exactly ONE of'), per-mode result scope (un_number returns every packing-group variant, hazard_class returns all entries in a class/division), and normalization examples ('1203', 'UN1203', 'un 1203' are equivalent). This exceeds the baseline but does not fully replace what the schema already documents.

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?

Specific verb plus resource plus scope: 'Look up European road dangerous-goods (ADR 2025) reference data' with the full set of returned fields enumerated (hazard class, packing group, Kemler number, etc.). Distinguishes from siblings by naming them in the Related line (adr_lq_eq_check, adr_exemption_calculator, consignment_calculator) with their distinct purposes.

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 instructs 'Provide exactly ONE of: un_number, search, hazard_class' and explains what each mode returns. The Related paragraph names alternatives and when to prefer them ('checks quantities against the LQ/EQ values returned here', '1.1.3.6 small-load points', 'flags dangerous-goods lines by UN number').

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation3/5

The tools cluster into clear domains and the descriptions are detailed, but there are several overlapping pairs: consignment_calculator vs shipment_summary, cbm_calculator vs unit_converter, and validate vs resolve_reference all have fuzzy boundaries. An agent could plausibly mis-select between the composite calculators or between identifier-handling tools despite the helpful cross-references.

Naming Consistency4/5

Naming is mostly consistent: reference tools use *_lookup, calculation tools use *_calculator, and checks use *_check. Exceptions like validate, resolve_reference, nearest_airport, and shipment_summary break the dominant pattern slightly, but all names are snake_case and generally predictable.

Tool Count3/5

At 25 tools, this sits at the heavy end of the range for an MCP server. The broad freight/logistics scope justifies many of them, but several single-purpose calculators could have been consolidated or grouped, making the surface feel larger and more redundant than necessary.

Completeness4/5

The server covers ADR dangerous-goods rules, multi-modal freight calculations, equipment lookups, identifier validation, customs/trade data, and emissions estimation. Minor gaps exist—no routing/geocoding, no SCAC/BIC coverage, no customs filing—but core freight-reference and calculation workflows are well supported.

Resources