Context7
Up-to-date docs for AI agents
作者提供的说明(英文原文)
Korean public procurement: bids, awards, contracts, statistics, products and mall search.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"procureport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/procureport",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add procureport -- npx -y @reneturcios/procureport mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"procureport": {
"command": "npx",
"args": [
"-y",
"@reneturcios/procureport",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"procureport": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/procureport",
"mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 CloudCorpRecords 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.0)于4天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js, Docker。
同一分类中有:Context7, Codebase Memory, Exa
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Up-to-date docs for AI agents
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.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
procureport opens up Korean public-procurement data — the Nara Market / data.go.kr API family — through one binary that serves a command-line interface and a stdio MCP server. It covers bid notices, successful bids (awards) and contracts, procurement statistics, the registered product catalogue, and the public shopping mall.
API-calling tools need a service key:
export NARAMARKET_SERVICE_KEY=<your data.go.kr service key>
Calls go to data.go.kr-style endpoints under a base URL you can override with NARAMARKET_API_URL (default https://apis.data.go.kr). Requests are shaped as {base}/{service}/{operation}?serviceKey={key}&{params}.
Four tools are purely local — they answer from a built-in catalogue of the four API services and their operations, and work with nothing configured: server_info, get_all_api_services_info, get_api_operations, and get_data_exploration_guide. Every other tool checks for the service key first and fails with a clean error before any request is attempted when it is missing.
npx @reneturcios/procureport server-info
Or run the container image:
docker run -i -e NARAMARKET_SERVICE_KEY=... ghcr.io/cloudcorprecords/procureport
The container defaults to the MCP server (see below). Pass CLI arguments to use it as a CLI instead.
procureport server-info
procureport services procureport operations shopping_mall procureport guide procureport crawl chair --page 1 --page-size 20 procureport attributes PRD-42 procureport recent-bids --days 7 --business-type 물품 procureport successful-bids 공사 procureport statistics-year 2025 procureport search-mall monitor --company Acme
procureport --version
Exit codes: 0 on success, 1 when a call fails (including a missing service key or an upstream API error), 2 for usage errors.
npx -y @reneturcios/procureport mcp
MCP client configuration:
{
"mcpServers": { "procureport": { "command": "npx", "args": ["-y", "@reneturcios/procureport", "mcp"], "env": { "NARAMARKET_SERVICE_KEY": " " } } } }
Basic:
| Tool | Input | What it returns |
|---|---|---|
crawl_list | query (optional), page, page_size (optional) | A page of the product list. |
get_detailed_attributes | product_id (required) | The detailed attributes of one product. |
server_info | (none) | Server identity, tool list, and service summary. Local. |
Generic API access (each takes operation (required) and an optional params object):
| Tool | Service |
|---|---|
call_public_data_standard_api | Bid notices, awards, and contracts. |
call_procurement_statistics_api | Procurement statistics — 14 operations. |
call_product_list_api | Product catalogue — 12 operations. |
call_shopping_mall_api | Shopping mall — 9 operations. |
Convenience:
| Tool | Input | What it returns |
|---|---|---|
get_recent_bid_announcements | days, business_type (both optional) | Bid notices over an automatically computed recent period. |
get_successful_bids_by_business_type | business_type (required) | Awards for a business type; a Korean name such as 물품, 용역, 공사 or 외자 is converted to its code automatically. |
get_procurement_statistics_by_year | year (required) | Procurement statistics for one year. |
search_shopping_mall_products | query (required), company (optional) | Shopping-mall products matching a name, optionally narrowed to one company. |
Exploration:
| Tool | Input | What it returns |
|---|---|---|
get_all_api_services_info | (none) | All four services with their operations. Local. |
get_api_operations | service (required) | The operations of one service. Local. |
call_api_with_pagination_support | service, operation (required), params, max_pages, page_size (optional) | Items aggregated across pages until a short page or the page cap. |
get_data_exploration_guide | (none) | A strategy guide for exploring the data. Local. |
Argument schemas in this rebuild are documented reconstructions from the public README of the original server (tool names and descriptions are documented; the README does not publish full schemas). The built-in catalogue's service operation counts follow the public spec (statistics 14, product list 12, shopping mall 9); individual operation names within the catalogue are documented reconstructions too.
npm install
npm run build # tsc -> dist/ npm test # node test runner over test/*.test.ts, no network (fake fetch fixtures) npm run dev # run the CLI from source via tsx
MIT — see LICENSE.