Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
US import duty research: HTS codes, Chapter 99 duties, MPF/HMF fees, landed cost. USITC data.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"tariff-resolver": {
"command": "npx",
"args": [
"-y",
"tariff-resolver"
]
}
}
}Run this in your terminal
claude mcp add tariff-resolver -- npx -y tariff-resolverPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"tariff-resolver": {
"command": "npx",
"args": [
"-y",
"tariff-resolver"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"tariff-resolver": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"tariff-resolver"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account opsloft, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.1.0) reached the registry 2 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
An MCP server that turns your AI assistant into a US import duty research tool — built on official USITC Harmonized Tariff Schedule data (US Government public domain, 35,000+ tariff lines).
Why now: since the de minimis exemption ended (Aug 29, 2025), every US-bound shipment needs an HTS code and duty payment — and 2025–26 rates keep changing by executive order.
Not affiliated with any government agency. Outputs are candidates/estimates for pre-broker screening — not customs, legal, or tax advice. Estimates exclude AD/CVD duties.
Requires Node.js ≥ 18.
claude mcp add tariff-resolver -- npx -y tariff-resolver
Or in any MCP client config:
{ "mcpServers": { "tariff-resolver": { "command": "npx", "args": ["-y", "tariff-resolver"] } } }
Claude Desktop (one-click): download tariff-resolver- .mcpb from Releases and double-click it — no terminal needed.
| Tool | What it does |
|---|---|
search_hs_candidates | Product description → top HTS candidates with rates + CBP CROSS ruling links |
calculate_tariff_scenario | HTS code + origin + value (+ weight) → structured JSON: base MFN/FTA rate, candidate Chapter 99 layers with per-layer match/confidence, sourced possibly_expired bucket, MPF/HMF |
watch_tariff_changes | Register HTS codes to a local watchlist |
check_tariff_updates | Diff current vs previous HTS revision — see exactly which rates changed |
dataset_info | Data revision date, row counts, source, license |
The server does the retrieval; your LLM does the reasoning. Chapter 99 rules are returned verbatim (with parsed adder_pct where applicable) so the model reads the actual exception chains instead of trusting a black-box calculation. Rates for 10-digit statistical suffixes inherit from their parent rate line. Headings the schedule marks as dead — terminated, suspended, expired — are filtered out and counted, and the USITC's own compiler_note rides along with any rule that carries one.
Status overrides. data/status_overrides.json is a short, sourced list of Chapter 99 headings whose collection has stopped, expired, or been suspended even though the schedule still prints them. A layer matching an entry is returned under possibly_expired with the entry's status, reason, source URL and as_of date instead of in layers. Every entry carries a CBP, Federal Register or USITC source; pull requests adding entries must include one.
What the data cannot tell you. The published schedule is wrong in both directions at any given moment, so every result carries a stacking_warning and the snapshot date. Provisions whose collection has already stopped keep printing with no end date — IEEPA and Section 122 headings are the recurring case — and newly proclaimed actions appear in the schedule days after they take effect. Totalling every layer the schedule prints yields a rate nobody is charged. Treat the layers as candidates, and verify collection status against CBP CSMS messages before relying on a stack.
One core, two front doors. All duty logic lives in tariff-resolver/core (pure TypeScript, no filesystem or network): resolveDuty(dataset, { hts, origin, value_usd?, ocean? }) — origin takes an ISO-3166 alpha-2 code or an English country name — returns the base line, separate MPF/HMF, every candidate Chapter 99 layer with match and confidence, a sourced possibly_expired bucket, and the snapshot date. The MCP tool calls it; so can any Node or edge runtime. A country name that is not recognised returns the ORIGIN_UNKNOWN error rather than a partial match, so a misspelled origin can never quietly resolve to a thinner stack of layers.
Ships with a full HTS snapshot, fetched from USITC's official JSON API (US Government public domain). Refresh anytime:
python3 scripts/fetch_hts.py # ~2 min, fails hard rather than write a partial dataset
dataset_info reports the revision date your queries run against.
tariff-resolver runs entirely on your machine and collects nothing:
scripts/fetch_hts.py refresh script contacts only the official USITC API.)Full policy: https://opsloft.dev/privacy
MIT. Tariff data is a work of the US Government (public domain).