tariffmonitor-mcp
This MCP server gives AI assistants two tools for looking up and calculating US import tariffs.
lookup_hts_code: Search the 19,856 HTS codes by product description or numeric prefix, returning up to 12 matching codes and descriptions.
calculate_tariff: Compute the full stacked tariff rate for a given HTS code and origin country (MFN base + Section 301 + IEEPA + reciprocal), including the current total rate and the projected rate after the November 10, 2026 cliff.
Optionally, provide an annual import value in USD to get the dollar impact of current duties and the additional cost from the cliff.
No API key required; uses a free public API and never fabricates rates—if data is unavailable, it says so.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@tariffmonitor-mcpWhat's the tariff on athletic footwear from China?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tariffmonitor-mcp
MCP server for the Tariff Exposure Monitor — a live US import tariff calculator covering 19,856 HTS codes.
Give Claude (or any MCP-compatible AI) the ability to look up real stacked tariff rates and project the November 10, 2026 cliff impact on any product.
What it does
Two tools:
Tool | What it does |
| Search 19,856 HTS codes by description or numeric prefix |
| Returns an estimated stacked rate (MFN base + Section 301 + Section 232) and flags the Nov 10, 2026 Section 301 exclusion expiry. Optional: annual import volume → dollar impact |
Example exchange — a real capture from the live API on 2026-09-11, not a mock-up:
You: What's the tariff on athletic footwear from China, and what does it cost me at $800k/year?
Claude: [calls lookup_hts_code query="athletic footwear", then calculate_tariff
hts_code="6404110000", origin_country="CN", annual_import_value_usd=800000]
Note: 6404110000 is not in the schedule. This rate is for heading 640411, resolved to 6404112030.
HTS 6404112030 - For men
Origin: CN
Rate stack:
MFN base rate: +0.00%
Section 301 (China trade enforcement): +7.50%
Total current rate: 7.50%
No cliff change projected for this code/country combination.
Dollar impact at $800,000/yr import value:
Current annual duties: $60,000Rates change, and a rate is per HTS code and origin country - treat the numbers above as the shape of the answer, not as a quote for your shipment. The tool never invents a rate: if the upstream is unreachable or the code is not in the schedule, it says so instead of estimating.
Related MCP server: mcp-hts
Install (Claude Desktop)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"tariffmonitor": {
"command": "npx",
"args": ["-y", "tariffmonitor-mcp"]
}
}
}Restart Claude Desktop. The lookup_hts_code and calculate_tariff tools appear automatically.
Install (Cursor / other MCP clients)
{
"mcp": {
"servers": {
"tariffmonitor": {
"command": "npx",
"args": ["-y", "tariffmonitor-mcp"]
}
}
}
}No API key required
The tool calls the free public API at adcreator-ai.com. No signup, no rate limits for reasonable use.
Related
Free tariff calculator — browser version
Official US Harmonized Tariff Schedule — the authoritative rates
Built by Dale Weaver / 0xpi.
Available Tools
2 toolscalculate_tariffA
Calculate the full stacked US import tariff rate for an HTS code from a specific origin country. Returns: base rate, each additional layer (Section 301, IEEPA, reciprocal), total current rate, and the projected rate after the November 10, 2026 cliff. Optionally computes dollar impact from annual import volume.
| Name | Required | Description | Default |
|---|---|---|---|
| hts_code | Yes | HTS code — at least 6 digits, up to 10 (e.g. "6404.11" or "6404110000"). Dots and spaces are ignored. | |
| origin_country | No | ISO-2 origin country code (e.g. "CN" for China, "VN" for Vietnam, "MX" for Mexico). Default: CN. | CN |
| annual_import_value_usd | No | Optional. Your annual import value in USD. If provided, the response includes the dollar cost of current duties and the additional cost from the Nov 10 cliff. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Given no annotations, the description details the multi-layer tariff computation, projected rates after a specific date, and optional dollar impact. It does not cover error handling or auth, but the computational behavior is well described.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured paragraph that front-loads the core purpose and then lists outputs and parameter details. Every sentence provides value with no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description explains the return structure thoroughly even without an output schema. Minor omission: no mention of error conditions or validity checks for HTS codes, but overall sufficient for a calculation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline 3. The description adds meaningful context: HTS code format flexibility (dots ignored), default country, and the effect of the optional import value parameter on response. This exceeds the schema alone.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states the tool calculates 'full stacked US import tariff rate' for a given HTS code and origin country. It lists the return components and optional dollar impact, clearly distinguishing it from the sibling lookup_hts_code.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for tariff rate calculation but provides no explicit guidance on when to prefer it over lookup_hts_code or what prerequisites exist. The agent must infer usage from the description alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
lookup_hts_codeA
Search for HTS (Harmonized Tariff Schedule) codes by description or numeric prefix. Returns up to 12 matching codes with descriptions. Use this before calculate_tariff when you only have a product description.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Product description (e.g. "athletic footwear") or HTS code prefix (e.g. "6404"). Min 2 characters. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses output limit (up to 12 results) and the prerequisite relationship. Could mention auth or rate limits but minimal for a search.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with purpose, then usage guideline. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a simple search tool: explains input, output, behavior, and when to use relative to sibling. No output schema needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, and the tool description adds no new information beyond what the schema already provides for the query parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches for HTS codes by description or numeric prefix and returns up to 12 matches. It distinguishes itself from the sibling tool calculate_tariff.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises to use this tool before calculate_tariff when only having a product description, providing clear context for when and why to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
v1.0.0- First observed
calculate_tariff - First observed
lookup_hts_code
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one for searching HTS codes by description, the other for calculating tariffs for a given code and origin country. There is no ambiguity.
Both tool names follow a consistent verb_noun pattern (lookup_hts_code, calculate_tariff), making them predictable and easy to understand.
With only 2 tools, the set is minimal but appropriate for its focused purpose of looking up tariffs. It could benefit from a couple more tools (e.g., list countries, get tariff history), but the count is not excessive.
The core workflow of finding an HTS code and calculating the tariff rate is covered. The calculations include multiple tariff layers and projected rates. Minor gaps exist, like lacking a tool to list supported origin countries or to update tariff data, but the essentials are present.
Maintenance
Related MCP Connectors
US import duty from the live HTS: Section 301/232 stacking, MPF, HMF. Refuses what it cannot price.
1US import tariff lookup against the official USITC Harmonized Tariff Schedule
US tariff lookup: HTS duty rates, Section 301 China lists, US–China tariff-cut flag.
41Landed cost, fees & profit calculators for cross-border Amazon, TikTok Shop and Shopify sellers.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceCalculates estimated import duties, taxes, and customs clearance rules for overseas purchases, with all tools being read-only and operating without external API calls.-
- AlicenseNot gradedqualityBmaintenanceProvides access to US import tariff rates via the USITC Harmonized Tariff Schedule, enabling natural language queries for tariff data.7 npmMIT
- FlicenseNot gradedqualityDmaintenanceProvides container shipping intelligence for AI agents, enabling demurrage & detention calculations, local charges, inland haulage rates, and CFS tariffs across multiple shipping lines, with pay-per-request USDC payments via x402.-
- AlicenseBqualityAmaintenanceTurns your AI assistant into a US import duty research tool, enabling HTS code lookup, landed-cost calculation, and tariff change tracking using official USITC data.587 npm2MIT