Claude Desktop connects to Pinterest through the CData Code Assist MCP for Pinterest using the Model Context Protocol (MCP).

When you launch Claude, it automatically detects MCP connections registered during setup. These connections are created and saved using the CData Code Assist MCP Configuration Tool, which is installed with the MCP server.

Each saved connection is recognized by Claude and can be referenced by name when asking questions.

Installing Claude

Claude Desktop は、Model Context Protocol（MCP）を使用して、サポートされているデータソースに対して自然言語クエリを実行できるスタンドアロンアプリケーションです。

MCP 経由でPinterest に接続するには、はじめにClaude Desktop アプリケーションをインストールする必要があります。

最新バージョンは公式Claude ダウンロードページ からダウンロードできます。

Claude Desktop をインストールした後、CData MCP Driver for Pinterest を使用してMCP 接続を設定します。

How Claude Uses the Server

When you ask Claude a question, it launches the corresponding MCP server connection, reads the available tool descriptions provided by the connector, and generates a secure query in the background.

There is no need to write SQL or teach Claude how to query your data. Each tool is self-describing, and Claude consumes those descriptions to determine how to retrieve the right information.

Example Prompts

After setup, you can ask Claude natural-language questions like:

• "What are my most saved pins from the last 30 days?"
• "Which of my pins have the highest engagement rate?"
• "Which boards have the most followers?"
• "Which of my boards have had no new pins added in the last 60 days?"
• "What is the total number of impressions across all pins last month?"
• "What is the average engagement rate per board?"
• "How did engagement change week over week for my top 5 boards?"
• "Who are my most recent followers?"
• "What is the follower growth rate over the past 90 days?"
• "What are the performance metrics for my promoted pins?"

Claude securely executes the query using the MCP server and responds using the live results from Pinterest.