Click on "Install 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., "@全球海关贸易数据 MCP 查一下最近三个月从日本进口的电子产品数据"
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.
全球海关贸易数据 MCP 服务 — 提供 238 个国家/地区的进出口贸易数据查询能力。
全球海关贸易数据 MCP 是一个 MCP（Model Context Protocol）服务器，对接 tradee.topease.net 海关智能体贸易数据平台，支持按进出口企业名称、产品关键字、HS编码、贸易时间、进出口类型及国家/市场/地区进行多维度联合查询，帮助大模型快速获取真实的全球贸易情报数据。
使用前需在 https://tradee.topease.net/ 注册并获取 API Key。
Related MCP server: Bidding MCP Server
🌍 全球覆盖：支持 238 个国家/地区的贸易数据查询
🔍 多维度查询：企业名称、产品关键字、HS 编码、贸易时间、进出口类型、国家联合筛选
🔐 安全认证：支持 API Key 认证，保护数据访问安全
🚀 两种传输模式：支持 stdio（桌面客户端）和 streamable-http（Web 应用）两种运行模式
📊 丰富的返回字段：包含企业信息、产品详情、贸易金额、数量、重量等完整数据
pip install topease-mcpuv add topease-mcpuvx topease-mcpgit clone https://github.com/topease020/topease-customs-mcp-server.git
cd topease-customs-mcp-server
uv pip install -e .在 Claude Desktop、Trae 等 MCP 客户端的配置文件中添加：
{
"mcpServers": {
"topease-customs-data": {
"command": "uvx",
"args": ["topease-mcp"],
"env": {
"TOPEASE_MCP_API_KEY": "<YOUR_API_KEY>"
}
}
}
}或使用 pip 安装的版本：
{
"mcpServers": {
"topease-customs-data": {
"command": "python",
"args": ["-m", "topease_mcp"],
"env": {
"TOPEASE_MCP_API_KEY": "<YOUR_API_KEY>"
}
}
}
}我们提供了公共的 streamable-http 服务，您可以直接使用以下配置：
配置项 | 值 |
服务类型 | 可流式传输的 HTTP (streamableHttp) |
服务 URL |
|
请求头 |
|
在 Claude Desktop、Trae 等支持 streamable-http 的客户端中添加配置：
{
"mcpServers": {
"【PRO】TOPEASE 贸易数据查询 stream http": {
"type": "streamableHttp",
"url": "https://mcp.topease.net/mcp",
"headers": {
"Authorization": "Bearer <YOUR_API_KEY>"
}
}
}
}本服务支持两种 API Key 配置方式（按优先级排序）：
环境变量（推荐）：设置 TOPEASE_MCP_API_KEY 环境变量
HTTP 请求头（streamable-http 模式）：通过 Authorization: Bearer <your_api_key> 请求头传递
查询海关贸易数据。支持多维度联合过滤。
参数 | 类型 | 必填 | 说明 | 默认值 |
| string | 否 | 企业名称（模糊匹配进口商/出口商） | - |
| string | 否 | 产品描述关键字，如 "led"、"valve" | - |
| string | 否 | HS 海关编码（前缀匹配），如 "8415" | - |
| string | 否 | 贸易类型： |
|
| string | 否 | 国家/地区名称（中文/英文/ISO编码均可），如 "China"、"美国"、"JP" | - |
| string | 否 | 起始日期，格式 YYYY-MM-DD | - |
| string | 否 | 结束日期，格式 YYYY-MM-DD | - |
| int | 否 | 页码 |
|
| int | 否 | 每页记录数（最大 20） |
|
| string | 否 | 排序字段： |
|
| string | 否 | 排序方向： |
|
注意：
company_name、product_keyword、hs_code、country至少填写一个
page_size最大值为 20，超出会自动截断
trade_type映射：import→1,export→0,all→2
每条记录包含以下字段（中文键名，便于大模型理解）：
字段 | 说明 |
| 单据编号 |
| HS 海关编码 |
| 产品描述 |
| 贸易类型（ |
| 进口商名称 |
| 出口商名称 |
| 数量 |
| 数量单位 |
| 重量 |
| 金额（USD），保留 4 位小数 |
| 贸易日期 |
| 原产国 |
| 原产国 ID |
同时包含分页信息：
字段 | 说明 |
| 总记录数 |
| 当前页码 |
| 每页记录数 |
| 总页数 |
请帮我查一下 LED 产品 2025 年从美国的进口数据，前 5 条大模型将自动调用：
{
"product_keyword": "led",
"country": "美国",
"trade_type": "import",
"date_from": "2025-01-01",
"date_to": "2025-12-31",
"page_index": 1,
"page_size": 5
}查询 IKEA SUPPLY AG 公司 2025 年从美国的出口记录{
"company_name": "IKEA SUPPLY AG",
"country": "美国",
"trade_type": "export",
"date_from": "2025-01-01",
"date_to": "2025-12-31"
}查询日本 8415 类目下的进口贸易数据{
"country": "Japan",
"hs_code": "8415",
"trade_type": "import"
}curl -X POST https://mcp.topease.net/mcp \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your_api_key" \
-d '{
"name": "search_customs_data",
"parameters": {
"product_keyword": "CABIN",
"page_index": 1,
"page_size": 10
}
}'topease-mcp/
├── src/
│ └── topease_mcp/
│ ├── __init__.py # 包初始化
│ ├── __main__.py # 模块入口：python -m topease_mcp
│ ├── main.py # MCP 服务入口，FastMCP 服务器定义
│ ├── customs.py # 海关数据模型与 API 调用服务
│ ├── country.py # 238 个国家/地区数据（含 ISO 编码）
│ ├── auth.py # API Key 认证模块
│ └── setting.py # 配置项（API 地址、端口）
├── pyproject.toml # 项目配置与依赖
├── README.md # 项目文档
└── .env.example # 环境变量示例main.py：定义 FastMCP 服务器，注册 search_customs_data 工具，处理 API Key 认证逻辑
customs.py：定义数据模型（CustomsRecord、CustomsQueryParams），封装 API 请求和响应处理
country.py：包含 238 个国家/地区数据，支持通过名称、英文名、ISO 编码查找国家 ID
auth.py：API Key 验证模块，支持环境变量配置有效密钥列表
setting.py：集中管理 API 基础地址和端口配置
# 1. 克隆项目
git clone https://github.com/TopEase-AI/topease-customs-mcp-server.git
cd topease-customs-mcp-server
# 2. 安装依赖
uv sync
# 3. 运行测试（如果有）
uv run pytest
# 4. 本地运行
uv run python -m topease_mcpA: 支持全球 238 个国家和地区，包括主要贸易经济体。可通过中文名、英文名、ISO 2/3 位编码查询。
A: 数据定期更新，具体请参考 topease.net 官网说明。
A: 访问 https://tradee.topease.net/ 注册账号即可获取。
A: API 有请求频率限制，具体限制请查看 API 文档。page_size 最大值为 20。
api_key？A: 为了简化大模型调用，API Key 通过环境变量或 HTTP 请求头配置，不再需要在每次调用时传入参数。
A: 修改 main.py 中 mcp.run() 的 transport 参数即可：
transport="stdio" — 桌面客户端模式
transport="streamable-http" — Web 应用模式
如果你使用 Codex、ChatGPT Agent Skills 或 Claude Code，可以安装配套 skill：
Skill 仓库：https://github.com/TopEase-AI/topease-customs-mcp-skill
Claude Code plugin marketplace：
claude plugin marketplace add TopEase-AI/topease-customs-mcp-skill
claude plugin install topease-customs-mcp@topease-agent-skills本仓库适合提交到 MCP server directory / registry，例如 Smithery、Glama、PulseMCP、mcpservers.org。提交时建议使用：
字段 | 建议值 |
Name | TOPEASE Customs MCP |
Repository |
|
Package |
|
Transport | stdio, streamable HTTP |
Remote endpoint |
|
Auth |
|
MIT License - 详见 LICENSE 文件。
欢迎提交 Issue 和 Pull Request！
查询海关贸易数据。支持按企业名称(company_name)、产品关键字(product_keyword)、HS编码(hs_code)、贸易时间(date_from/date_to)、进出口类型(trade_type)及原产国(country)进行多维度联合查询。
| Name | Required | Description | Default |
|---|---|---|---|
| company_name | No | 企业名称（模糊匹配进口商/出口商名称），会做后置过滤。 | |
| product_keyword | No | 产品描述关键字，例如 "CABIN"、"手机"。 | |
| hs_code | No | HS海关编码（前缀匹配），例如 "8415"。 | |
| trade_type | No | 贸易类型：import(进口)、export(出口)、all(全部，默认)。 | all |
| country | No | 数据源国（英文名），例如 "Japan"、"China"。 | |
| date_from | No | 贸易起始日期，格式 YYYY-MM-DD。默认 2025-01-01。 | |
| date_to | No | 贸易结束日期，格式 YYYY-MM-DD。默认当前时间。 | |
| page_index | No | 页码，默认为1。 | |
| page_size | No | 每页记录数，默认为20，最大100。 | |
| sort_by | No | 排序字段，默认 tradedate。支持排序字段；tradedate,quantity,weight,uusd | tradedate |
| sort_order | No | 排序方向，asc/desc，默认 desc。 | desc |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It does not mention whether the tool is read-only, has rate limits, requires authentication, or any side effects. The name implies read operation, but no explicit statement.
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 two sentences, extremely concise, and front-loads the core purpose. Every word is meaningful, 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?
Given 11 parameters, full schema coverage, and an output schema, the description is adequate but does not mention output format, pagination, or that all parameters are optional. It could provide higher-level context about result structure.
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%, so baseline is 3. The description enumerates key parameters but adds no new meaning beyond what the schema already provides for each 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 queries customs trade data and lists specific supported dimensions (company name, product keyword, etc.), providing a specific verb and resource. No sibling tools exist, so differentiation is not required.
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 provides no guidance on when to use this tool, prerequisites, or alternatives. It simply lists capabilities without context for appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Only one tool exists, so there is no possibility of confusion or misselection.
The single tool name 'search_customs_data' follows a clear verb_noun pattern, appropriate for its function.
A server focused on global customs trade data with only one search tool feels under-scoped; a few more tools (e.g., for metadata or export) would be expected.
The tool provides rich search capabilities, but lacks any additional operations like listing HS codes, retrieving trade statistics, or data export, leaving notable gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Global customs trade data and company registry. Search shipments, and look up legal entities.
Global B2B trade: verified manufacturers, product search, sanctions screening, HS codes.
Classify, validate & verify HS codes and access tariff compliance data for cross-border trade
Ocean & multimodal freight intelligence: rates, landed cost, transit, customs, risk, ship decisions
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TopEase-AI/topease-customs-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server