広告掲載
MCP.so
ログイン

Stocky MCP Server

@joelio

リポジトリ

基本情報

カテゴリ

その他

トランスポート

stdio

作者

joelio

投稿者

Joel Merrick

Stocky MCP Server について

Find beautiful royalty-free stock images 📸

#photos#stock#royalty-free#image

Stocky MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "stocky": {
      "command": "python",
      "args": [
        "/path/to/stocky_mcp.py"
      ],
      "env": {
        "PEXELS_API_KEY": "your_pexels_key",
        "UNSPLASH_ACCESS_KEY": "your_unsplash_key"
      }
    }
  }
}

Stocky MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Stocky?

Stocky is a Model Context Protocol (MCP) server that searches and retrieves royalty-free stock images from multiple providers (Pexels and Unsplash) simultaneously. It is built for Python developers who need to find stock photos with rich metadata inside MCP-enabled applications.

How to use Stocky?

Install Stocky by cloning its repository, installing dependencies with pip install -r requirements.txt, and adding Pexels and Unsplash API keys to a .env file. Run the server with python stocky_mcp.py, then configure your MCP client to launch the script with the required environment variables. Use the search_stock_images tool to find images and get_image_details to retrieve full metadata for a specific image.

Key features of Stocky

  • Multi-provider search across Pexels and Unsplash simultaneously.
  • Rich image metadata including dimensions, photographer info, and licensing.
  • Pagination support for browsing large result sets.
  • Graceful error handling for API failures.
  • Async performance with concurrent API calls.
  • Provider flexibility – search all providers or a specific one.

Use cases of Stocky

  • Quickly find royalty-free images for blog posts and marketing materials.
  • Populate a design mood board with diverse stock photos from multiple sources.
  • Automate image selection in content creation workflows by querying via MCP.
  • Compare image options from Pexels and Unsplash without switching platforms.
  • Integrate stock photo search into AI assistants or developer tools.

よくある質問

1

What runtime or dependencies does Stocky require?

Stocky requires Python 3.8 or newer and its dependencies are installed via `pip install -r requirements.txt`. It is MCP-compatible.

2

How do I get API keys for Stocky?

You need free API keys from Pexels (get at pexels.com/api) and Unsplash (sign up at unsplash.com/developers). Add them as `PEXELS_API_KEY` and `UNSPLASH_ACCESS_KEY` in your `.env` file or environment configuration.

3

Where do the images come from and where is my data stored?

All images are fetched in real time from Pexels and Unsplash via their APIs. Stocky does not store images or personal data locally; search results and metadata are returned directly to the client.

4

Are there any rate limits when using Stocky?

Yes. Pexels allows 200 requests per hour, Unsplash allows 50 requests per hour on the demo plan and 5000 per hour on the production plan.

5

How does Stocky handle authentication and transport?

Authentication is handled via environment variables containing API keys. Stocky runs as a local Python process over standard I/O (MCP stdio transport); no network authentication is needed beyond the API keys.

コメント

「その他」の他のコンテンツ

Volley.sh

Volley

A good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi

FastMCP v2 🚀

jlowin

🚀 The fast, Pythonic way to build MCP servers and clients.

26.0K

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Yuppsy

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code

広告掲載