Salesforce MCP Server

What does “Salesforce” MCP Server do?

The Salesforce MCP (Model Context Protocol) Server is a tool designed to facilitate seamless integration between AI assistants and Salesforce, one of the most widely used customer relationship management (CRM) platforms. By leveraging MCP, this server enables AI-powered workflows to interact programmatically with Salesforce features such as sending emails and deploying Apex code. This direct connection empowers developers and AI clients to automate various Salesforce tasks, streamline business processes, and enhance productivity by connecting large language models to critical enterprise data and actions in Salesforce. The server is particularly valuable for developers and organizations looking to augment their Salesforce usage with AI-driven automation, reducing manual effort and minimizing context-switching between tools.

List of Prompts

No prompt templates are explicitly documented in the repository files or README.

List of Resources

No explicit MCP resources are listed or described in the repository files or README.

List of Tools

• Send Email: Allows the server (and thus the AI client) to send emails through Salesforce using MCP tools.
• Deploy Apex Code: Provides the ability to deploy Apex code to a Salesforce org programmatically.

Further details about tool methods and their parameters are not documented in the repository files or README.

Use Cases of this MCP Server

• Automated Salesforce Emailing: Streamline workflows by programmatically sending customer or internal emails via Salesforce, reducing manual steps for communication.
• Apex Code Deployment: Enable rapid iteration and deployment of custom business logic to Salesforce directly from AI workflows, accelerating development cycles.
• AI-driven CRM Automation: Allow AI assistants to automate repetitive Salesforce tasks, such as sending notifications or updating records, freeing up human resources.
• Enhanced AI Support for Sales Teams: Integrate AI-powered suggestions or actions within Salesforce, improving decision-making and response times.
• Workflow Integration: Connect Salesforce processes to broader enterprise automation flows, enabling seamless data and action sharing between platforms.

How to set it up

Windsurf

No specific setup instructions or configuration examples for Windsurf are provided in the repository.

Claude

1. Prerequisites: Ensure Node.js and npm (or yarn) are installed.
2. Install dependencies:

   npm install
   

3. Configure Salesforce credentials: Create utils/credentials.js as shown in the README.
4. Update configuration: Use the provided claude_desktop_config.json as a template.
5. Run the server:

   node server.js
   

6. Sample JSON configuration (from claude_desktop_config.json):

   {
     "mcpServers": {
       "salesforce": {
         "command": "node",
         "args": [
           "/absolute/path/to/your/server.js"
         ],
         "env": {
           "SALESFORCE_USERNAME": "your_username",
           "SALESFORCE_CLIENT_ID": "your_clientid",
           "SALESFORCE_PRIVATE_KEY_PATH": "/path/to/private.key"
         }
       }
     }
   }
   

7. Securing API keys: Use environment variables as shown in the env section above.

Cursor

No specific setup instructions or configuration examples for Cursor are provided in the repository.

Cline

No specific setup instructions or configuration examples for Cline are provided in the repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "salesforce": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “salesforce” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Does the server support Roots? Not documented
Does the server support Sampling? Not documented

Between the two tables, the Salesforce MCP server provides basic but useful Salesforce integration tools, with clear setup for Claude and general Node environments. However, documentation is sparse (especially for prompts/resources), and support for multiple platforms or advanced MCP features is not detailed. I’d rate this MCP server integration a 5/10 for completeness and usability based on available information.

MCP Score