docker-hub-mcp

docker-hub-mcp

MCP server for querying Docker Hub image statistics, including pull counts, stars, descriptions, and publisher catalogs. No API key required.

Category
访问服务器

README

Docker Hub MCP Server

A Model Context Protocol (MCP) server for querying Docker Hub image statistics. Provides pull counts, star counts, descriptions, official/verified status, and publisher catalogs through the public Docker Hub API — no API key required.

Features

  • get_image_stats(image) — single image metadata (pulls, stars, last_updated, description, is_official, is_verified)
  • search_images(query, limit) — keyword search across Docker Hub
  • batch_image_stats(images) — concurrent lookup for up to 100 images
  • get_publisher_images(publisher, limit) — catalog all images from a namespace (e.g. library, bitnami, grafana)

Installation

uv (recommended)

uvx docker-hub-mcp

pip

pip install docker-hub-mcp
docker-hub-mcp

Configuration

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "docker-hub-mcp": {
      "command": "uvx",
      "args": ["docker-hub-mcp"]
    }
  }
}

Cursor / VS Code

Add to your MCP configuration:

{
  "mcpServers": {
    "docker-hub-mcp": {
      "command": "uvx",
      "args": ["docker-hub-mcp"]
    }
  }
}

Hermes Agent (MCP Gateway)

Add to ~/.hermes/gateway.yaml:

docker-hub-mcp:
  command: uvx docker-hub-mcp
  lazy_spawn: true
  timeout: 30s
  env: {}

Tools

Tool Description Key Params
get_image_stats Pull count, star count, last updated, description, official/verified status image (required) — "nginx" or "grafana/grafana"
search_images Keyword search, ranked results query (required), limit (default 50)
batch_image_stats Concurrent lookup of up to 100 images images (required, list)
get_publisher_images All images in a namespace publisher (required), limit (default 100)

Examples

# Get stats for nginx
get_image_stats({"image": "nginx"})
# → pull_count: 13.2B, star_count: 21K, is_official: true

# Search for postgres
search_images({"query": "postgres", "limit": 5})
# → ranked results with pulls, stars, official flags

# Batch compare web servers
batch_image_stats({"images": ["nginx", "httpd", "caddy", "traefik"]})

# Catalog a publisher
get_publisher_images({"publisher": "bitnami", "limit": 25})

Data Source

Uses the Docker Hub API (/v2/repositories and /v2/search).

  • Auth: None required for public data
  • Rate limit: ~4,400 requests per 6 hours (unauthenticated)

Development

git clone https://github.com/GeniusTechnoMystic/docker-hub-mcp.git
cd docker-hub-mcp
uv sync
uv run docker-hub-mcp

Run tests:

uv run pytest tests/

Related Projects

Other Docker Hub MCP servers in the ecosystem:

Project Language Tools Auth Tests Install
docker/hub-mcp (official) TypeScript 13 PAT (optional) Yes npm install
lucadruda/docker-hub-mcp-server TypeScript 49 (dynamic) PAT None npm install
RSVINEETHA/DockerHub-MCP-Server TypeScript 8 PAT (required) None npm install
This one (ours) Python 4 None 46 tests uvx / pip install

Our differentiators

  • Zero auth — no API key, no PAT, no Docker account needed. Just uvx docker-hub-mcp
  • Python ecosystem — only Python implementation. Install via pip or uvx, no Node.js needed
  • Batch operations — batch_image_stats is unique — no competitor offers concurrent multi-image lookup
  • Test coverage — 46 tests with mocked HTTP (pytest-httpx), the most thorough test suite of any Docker Hub MCP server
  • MIT license — permissive, easy to embed

When to use the alternatives

  • docker/hub-mcp — if you need repository management (create, update, delete), tag listing, or Docker Hardened Images. Requires PAT for write operations.
  • lucadruda/docker-hub-mcp-server — if you need full Docker Hub API coverage (collaborators, webhooks, stars, namespaces). Requires PAT.
  • RSVINEETHA/DockerHub-MCP-Server — minimal alternative, requires PAT.

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