【MCP Server】Salesforce × Claude Desktop 連携ガイド | AI でデータを徹底活用

Model Context Protocol (MCP) is an emerging, open-source standard for connecting LLMs with external services and data sources. Through MCP Servers, AI clients can perform actions like opening Jira tickets, posting Slack messages, committing GitHub branches and more. With CData MCP Servers, these capabilities expand exponentially.

In this article, we guide the reader through installing the CData MCP Server for Salesforce, configuring the connection to Salesforce, and asking questions of the data in Claude Desktop.

Prerequisites

You need to download Claude Desktop (download) and create an account before continuing.

Overview

Here's a quick overview of the steps:

1. Download and install the CData MCP Server for Salesforce
2. Configure the connection to Salesforce
3. Ask questions about the data in Claude Desktop

Step 1: Download and install the CData MCP Server

1. To begin, navigate to https://www.cdata.com/solutions/mcp/connectors and download the CData MCP Server for Salesforce.
2. Find and double-click the installer to begin the installation.
3. Follow the prompts to complete the installation.

When the installation is complete, you are ready to configure your MCP Server by connecting to Salesforce.

Step 2: Configure the connection to Salesforce

1. After installation, the CData MCP Server configuration wizard should open automatically.

   NOTE: If the wizard does not open automatically, search for "CData MCP Server" in the Windows search bar and double-click the application.

2. Click the dropdown menu in MCP Configuration > Configuration Name and select ""
3. Name the configuration (e.g. "cdatasalesforce") and click "OK."

   NOTE: This name is used as the name for the MCP server and as the prefix for all of the MCP Server's tools.

   

4. Connecting to Salesforce

   Salesforce 接続プロパティの設定方法

   埋め込みOAuth（UI でのログイン）による接続設定

   それでは、Salesforce への接続について説明していきましょう。最も簡単な方法として、Salesforce にログインする際と同様にUI 上からログインするだけで接続設定が完了します（埋め込みOAuth）。この方法をご利用になる場合は、「Salesforce への接続」をクリックしてください。

   標準認証の設定

   埋め込みOAuth 以外の方法を利用する場合、以下の3つの認証方式をご利用いただけます。標準的な認証方式では、以下の情報が必要となります。

   • ユーザー名
   • パスワード
   • セキュリティトークン

   セキュリティトークンの取得方法については、セキュリティトークン取得手順をご確認ください。

   OAuth 認証の設定

   ユーザー名とパスワードによる認証がご利用いただけない（避けたい）場合は、OAuth 認証をお使いいただけます。

   SSO（シングルサインオン）の設定

   最後に、IDプロバイダー経由でのシングルサインオンをご利用になる場合は、以下のプロパティを設定してください。

   • SSOProperties
   • SSOLoginUrl
   • TokenUrl

   より詳細な設定手順については、ヘルプドキュメントの「はじめに」セクションをご確認ください。

   Enter the appropriate connection properties in the configuration wizard.

   
5. Click "Connect" to authenticate with Salesforce.
6. Finally, click "Save Configuration" to save the MCP server.

   NOTE: This saves the configuration details to a separate file and updates the Claude Desktop configuration file (claude_desktop_config.json) to start the CData MCP Server when the Claude Desktop client starts.

With the CData MCP Server configured, you are ready to start asking questions of your live data from Claude.

Step 3: Ask AI for answers from live Salesforce のデータ

Now that we have installed the CData MCP Server and configured a connection, we are ready to start with Salesforce のデータ in Claude Desktop.

1. Open Claude Desktop. It may take a moment for the MCP Servers to start, but you will see the list of servers and tools available in the Claude interface (look for the settings icon below the prompt bar).

   You can individually enable and disable specific tools by clicking on the server name.

2. Now that you have connected, you can ask Claude questions about the Salesforce のデータ. For example: "Can you give me a quantitative analysis about my closed-won opportunities by industry?"

   NOTE: Claude may need to explore the Salesforce のデータ to make sense of it before it can begin answering questions of the data. The tabular model presented by CData alongside the database tools available simplify the data exploration and analysis for an LLM.

   

Connect your AI to your data today!

CData MCP Servers make it easier than ever for LLMs to work with live enterprise data. To explore the technology hands-on, download a free, 30-day trial or visit the CData Community to share insights, ask questions, and help shape the future of enterprise-ready AI.