rhr-mcp

rhr-mcp

MCP server that gives AI agents structured access to Public Procurement Registry data, allowing natural language queries for planned procurements, open tenders, contract awards, buyers, and winning suppliers.

Category
访问服务器

README

RHR MCP

MCP server that gives AI agents structured access to Public Procurement Registry data. Query procurements, awards, buyers, and winning suppliers using natural language through any MCP-compatible client.

Tech Stack

  • Runtime — Bun >= 1.4.0
  • Language — TypeScript 7
  • Database — PostgreSQL
  • Query builder — Kysely
  • Validation — Zod
  • Tooling — Oxfmt and Oxlint

Prerequisites

Download open data

Download the public datasets from:

https://riigihanked.riik.ee/rhr-web/#/open-data

Place the unzipped files directly in the data/ folder at the project root. For example, a full year looks like:

  • HT_2025_1.xml
  • HT_2025_2.xml
  • HT_2025_3.xml
  • HT_2025_4.xml
  • HT_2025_5.xml
  • HT_2025_6.xml
  • HT_2025_7.xml
  • HT_2025_8.xml
  • HT_2025_9.xml
  • HT_2025_10.xml
  • HT_2025_11.xml
  • HT_2025_12.xml
  • HLST_2025_1.xml
  • HLST_2025_2.xml
  • HLST_2025_3.xml
  • HLST_2025_4.xml
  • HLST_2025_5.xml
  • HLST_2025_6.xml
  • HLST_2025_7.xml
  • HLST_2025_8.xml
  • HLST_2025_9.xml
  • HLST_2025_10.xml
  • HLST_2025_11.xml
  • HLST_2025_12.xml

HT_*.xml files are contract notices. HLST_*.xml files are contract award notices. Add any year the same way (HT_2024_1.xml, HT_2027_1.xml, and so on) — ingest picks up every matching file in data/.

Getting Started

git clone https://github.com/margusliinev/rhr-mcp.git
cd rhr-mcp
cp .env.example .env
bun install
docker compose up -d
bun run migrate
bun run ingest
bun run dev

The MCP endpoint is available at http://localhost:3002/mcp.

Use with Cursor

With the server running, add this to your Cursor MCP config (.cursor/mcp.json):

{
    "mcpServers": {
        "RHR": {
            "url": "http://localhost:3002/mcp"
        }
    }
}

Then restart MCP / reload Cursor so the RHR server shows up.

Available tools

Tool Description
get-organization Get an organization by id or registry code
get-procurement Get a procurement with buyers, lots, and award summaries
get-award Get an award with suppliers, lot, and procurement summary
list-organization-procurements List procurements where an organization is a buyer
list-organization-awards List awards where an organization is a winning supplier
list-procurement-lots List lots for a procurement, with award summaries linked by lot id
search-organizations Search organizations by name or registry code
search-procurements Search and filter procurements by text, status, CPV, value, and more
search-awards Search awards by amount, date, CPV, result, and supplier

Scripts

Command Description
bun run dev Start development server
bun run start Start production server
bun run migrate Apply database migrations
bun run ingest Load RHR data from data/ into Postgres
bun run format Format code
bun run lint Lint code
bun run typecheck Typecheck

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选