SudnoKontrol MCP

SudnoKontrol MCP

Enables searching Ukrainian national vessel registries by registration number, name, or owner, retrieving full vessel records, and querying registry statistics, all without an API key.

Category
访问服务器

README

SudnoKontrol MCP

Model Context Protocol server for the Ukrainian national vessel registry — search vessels by registration number, name or owner, look up full registry records, and query aggregate statistics. Exposes the public data of the Державний судновий реєстр України (State Ship Registry) and the Суднова книга України (Ship Book).

Data is read-only and public — no API key required.

  • Hosted endpoint (recommended): https://api.sk.ukrfish.org/mcp (Streamable HTTP)
  • Official docs: https://sk.ukrfish.org/api-docs and https://sk.ukrfish.org/info/ai-agents
  • Discovery: https://sk.ukrfish.org/llms.txt

Tools

Tool Description
search_vessel_registries Free-text + structured search across both national registries. Deterministic ordering: exact registration-number matches first. Supports Cyrillic/Latin and separator-insensitive numbers (УПС-0129 ≡ УПС 0129 ≡ UPS-0129).
lookup_vessel Exact vessel lookup by normalized registration number. Returns full registry record.
get_registry_stats Aggregate public vessel counts ("how many vessels...").
get_dataset_metadata Dataset context: sources, import dates, record counts, fields.

Every search/lookup result includes a web_url → https://sk.ukrfish.org/registry?vessel=<reg> where users can order an official registry excerpt (PDF with QR-code verification, 99,00 грн).

Quick start — hosted server

Claude Code / Claude Desktop

claude mcp add --transport http sudnokontrol https://api.sk.ukrfish.org/mcp

Cursor

Settings → MCP → Add new MCP server → Name sudnokontrol, Type HTTP, URL https://api.sk.ukrfish.org/mcp.

Windsurf

Windsurf → MCP → Add server → https://api.sk.ukrfish.org/mcp.

Any MCP client (streamable HTTP)

URL:  https://api.sk.ukrfish.org/mcp
Auth: none (public, IP rate-limited)

Run it yourself

The server proxies the public API and needs no credentials.

# stdio (for Claude Desktop "command" servers)
npx sudnokontrol-mcp

# HTTP (streamable)
npx sudnokontrol-mcp http
# or: PORT=9000 HOST=127.0.0.1 npx sudnokontrol-mcp http

Install from this repo directly:

npm install -g github:ailubes/sudnokontrol-mcp

To point at a different base (e.g. your own deployment):

SUDNOKONTROL_API=https://api.sk.ukrfish.org/api/ai npx sudnokontrol-mcp

From source:

npm install
npm run build
node dist/index.js        # stdio
node dist/index.js http   # HTTP on :8958/mcp

Connect to your local instance

claude mcp add --transport http local-sudnokontrol http://127.0.0.1:8958/mcp

API (underlying REST, no MCP needed)

Endpoint Purpose
GET https://api.sk.ukrfish.org/api/ai/openapi.json OpenAPI 3.1 spec
GET https://api.sk.ukrfish.org/api/ai/tools Function-calling tool definitions (JSON Schema)
GET https://api.sk.ukrfish.org/api/ai/meta Dataset context
GET https://api.sk.ukrfish.org/api/ai/registry/search?q= Search
GET https://api.sk.ukrfish.org/api/ai/registry/lookup/{reg} Lookup
GET https://api.sk.ukrfish.org/api/ai/stats Aggregates

Rate limit: 300 requests / 15 min / IP on /api/ai/*. Search/meta/stats responses cached 60s.

Example

User: Is the vessel УПС-4249 registered?

Agent calls: lookup_vessel {"registration_number": "УПС-4249"}
Response: { registration_number: "УПС-4249", name: "ua 5614 KV", owner_name: "ТОВ Соціальні ініціативи Запоріжжя", source: "registry", web_url: "https://sk.ukrfish.org/registry?vessel=УПС-4249", ... }

License

MIT

Disclaimer

This is an open-source MCP adapter for the public data of the Ukrainian vessel registries operated by SudnoKontrol. It is not an official government service.

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