MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

MCP server · Data access / search

Sanctions & Tariff Lookup

Screen names on US, UN, UK and EU sanctions lists; US HTS codes and total duty by origin.

Checks passed
12 / 22

2 failed · 8 not measured

Median response
123 ms

Median of successful probes over 7 days

30-day uptime
Not measured

Share of countable probes over 30 days, including daily rollups. Auth challenges are excluded.

Discovered tools
7

Tool definitions returned by this server

Independent monitoring

Health & checks

Status history

Outdated check

Last connection measurement is over 24 hours old. Current availability is unknown.

Last checked
Check summary by test group
Test areaPassedFailedUnmeasured
ConnectionCan a client connect and discover tools?
500
Reliability & speedDoes it respond consistently and quickly?
004
Access & authenticationWhat is required to use this server?
102
Tool qualityAre the tool definitions usable by an agent?
400
Publisher identityCan the publisher be traced to its source?
222

Unmeasured means there is not enough evidence to decide. How these checks work

Inspect individual checks 22 recorded

Core

  • Pass
    Reachable

    Latest probe returned HTTP 200 in 123 ms.

  • Pass
    Valid handshake

    protocolVersion 2025-11-25, serverInfo.name sanctions-tariff-lookup.

  • Pass
    Lists tools

    tools/list returned 7 tools.

  • Pass
    Current protocol

    Negotiated 2025-11-25. The bar is 2025-06-18 or newer.

  • Pass
    HTTPS

    The endpoint URL is https.

Performance

  • Not measured
    Fast (p50)

    Median latency 123 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.

  • Not measured
    Consistent (p95)

    95th percentile 123 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.

  • Not measured
    Reliable (uptime)

    1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.

  • Not measured
    Stable tool list

    Fewer than two successful probes in 30 days, so tool-list stability is not measured.

Access

  • Pass
    Open access

    tools/list succeeded with no credential, and the record declares none.

  • Not measured
    Standard auth

    Auth is not required, so the OAuth metadata check does not apply.

  • Not measured
    Free tier cited

    No publisher quote has been checked.

Tools

  • Pass
    Tools described

    Every tool description is at least 20 characters.

  • Pass
    Valid input schemas

    Every inputSchema is a JSON Schema object.

  • Pass
    Parameters documented

    27 of 27 parameters have a description (100%). The bar is 80%.

  • Pass
    Safety hints

    Every tool sets readOnlyHint or destructiveHint.

Publisher

  • Pass
    Verified namespace

    Listed in the Official MCP Registry.

  • Fail
    Website matches publisher

    The website host does not match the reverse-domain namespace.

  • Fail
    Source repo linked

    No repository URL is on file.

  • Not measured
    Repo owner matches

    This namespace is not an io.github login, so the owner comparison does not apply.

  • Pass
    Recently updated

    Updated 2026-11-10T03:48:12.469178Z, within 180 days.

  • Not measured
    Open-source licence

    No GitHub repository to ask about a licence.

Start using Sanctions & Tariff Lookup

Connect to this server

Choose your client, copy the configuration, then enable the server in your client’s MCP settings.

Run this command in your terminal, then restart Claude Code.

Claude Code

claude mcp add --transport http sanctions-tariff-lookup https://tradecheck.trystarrynightops.com/mcp

Capabilities

Tools 7

compare_origins

Computes the same duty total as duty_stack for one 8- or 10-digit HTS line across up to 30 countries of origin and returns them sorted from the lowest total, each with its base rate, the Chapter 99 headings applied and the number of open questions. Without "origins" it compares 20 large sources of U.S. imports. Each row uses default assumptions (no trade-agreement preference claimed, no special use).

Discovered
duty_stack

Adds up the U.S. import duty on one 8- or 10-digit HTS line for goods of one country of origin under the current HTS revision: the column 1 (or column 2) rate plus the Chapter 99 additional duties in force that this tool models (Section 232 actions on metals, vehicles and other products, the Section 301 actions on China, Brazil and the 60 economies of the forced-labor action, and the Section 338 duties on Canada). Returns each layer with its Chapter 99 heading, rate and U.S. note, the exemptions it found, the total, the assumptions it made with what changes if an assumption is wrong, measures that are printed in the schedule but not in force, and what is not covered (for example antidumping and countervailing duties). When a question cannot be settled from the code and origin, the result says so and gives a range.

Discovered
hts_rate

Looks up one HTS code (4, 6, 8 or 10 digits, with or without dots) in the current Harmonized Tariff Schedule of the United States and returns its description, parent hierarchy, general, special (trade program) and column 2 duty rates, units, footnotes, Chapter 99 cross-references and the lines below it.

Discovered
hts_search

Searches the descriptions in the current Harmonized Tariff Schedule of the United States (USITC) for product words and returns matching 8- and 10-digit HTS lines with code, description, parent headings, general (column 1) duty rate and unit of quantity. Some everyday terms (for example laptop, drone, e-bike) are mapped to HTS wording, and the mapping is shown in the result.

Discovered
list_status

Returns the versions of the mirrored data: each screening dataset (U.S. CSL, UN, UK, EU) with its as-of date, file timestamp, entry count and last update check, each list's name, agency, entry count and as-of date, the current HTS revision, and when the mirror was last built and last checked for updates.

Discovered
screen_parties

Screens up to 25 names in one call against the same list mirrors as screen_party (U.S. Consolidated Screening List, UN, UK and, when loaded, EU lists) and returns only the best possible match per name (or no match at the threshold) in compact form, with a summary count.

Discovered
screen_party

Screens one person, company, vessel or aircraft name against a mirrored copy of the U.S. Consolidated Screening List (trade.gov), which combines the export screening lists of the Departments of Commerce, State and the Treasury, including OFAC's Specially Designated Nationals (SDN) list and the BIS Entity List, and against mirrored copies of the UN Security Council Consolidated List, the UK Sanctions List (FCDO) and, when loaded, the EU consolidated financial sanctions list. Matches primary names and aliases while tolerating differences in case, accents, punctuation, word order, company suffixes (LLC, Ltd, GmbH, OOO), small typos, common transliterations and added place or office words (a city, a country, "head office", "branch"). Returns ranked possible matches with score, matched alias, list, programs, entity type, addresses, countries, IDs, a link to the official entry or list and the list's as-of date, or a no-match result at the chosen threshold.

Discovered

Recent measurements

Probe history

View status
Latest stored probes. Raw probe rows are kept for 14 days.
CheckedResultResponseTools
Connected123 ms7