Claude Desktop connects to Slack through the CData Code Assist MCP for Slack 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Slack 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 Slack 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 the most active channels in the last 7 days?"
• "List unread messages directed at me in private channels."
• "Find all messages containing the word "urgent" from last week."
• "What are the most common keywords used in #support over the past 30 days?"
• "Which team members have been tagged the most in the last month?"
• "List the most active threads in #engineering this week."
• "Show me threads where my messages haven’t received a reply."
• "Find all messages with file attachments in #design."
• "Show me all messages where I was mentioned but didn’t respond."
• "List all links shared in #sales this quarter."

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