Salesforce MCP Server

What does “Salesforce” MCP Server do?

The Salesforce MCP (Model Context Protocol) Server acts as a connector that allows AI assistants and large language models (LLMs) to interact directly with Salesforce data. By exposing Salesforce’s rich set of APIs, this server enables development workflows such as querying databases with SOQL, searching with SOSL, retrieving metadata, managing records, and executing tooling or REST API requests. It streamlines the integration between AI clients and Salesforce, empowering developers and AI agents to automate business processes, extract insights, and manage Salesforce resources programmatically. This connectivity enhances productivity by making Salesforce’s data and services accessible in any AI-driven workflow.

List of Prompts

No explicit prompt templates are mentioned in the repository.

List of Resources

No specific MCP “resources” are enumerated in the available documentation.

List of Tools

• SOQL Query Execution
  Enables LLMs to run Salesforce Object Query Language (SOQL) queries against Salesforce data.
• SOSL Search Execution
  Permits performing Salesforce Object Search Language (SOSL) searches for text across multiple objects.
• Metadata Retrieval
  Fetches metadata related to Salesforce objects, such as field names, labels, and types.
• Record Management
  Supports retrieval, creation, updating, and deletion of Salesforce records.
• Tooling API Request Execution
  Allows execution of Salesforce Tooling API requests for advanced development and debugging.
• Apex REST Request Execution
  Enables use of custom Apex REST endpoints exposed in Salesforce.
• Direct REST API Calls
  Facilitates making direct REST API calls to Salesforce for custom integrations.

Use Cases of this MCP Server

• Automated Salesforce Database Management
  Easily query, update, create, and delete Salesforce records programmatically using LLMs, streamlining CRM data operations.
• Codebase Exploration for Salesforce Developers
  Retrieve object metadata and explore the structure of Salesforce objects and fields, aiding in rapid development and debugging.
• API Integration and Orchestration
  Use AI agents to orchestrate Salesforce REST and Tooling API calls as part of larger automation or workflow pipelines.
• Salesforce Data Search and Reporting
  Execute powerful text searches and structured queries for analytics or reporting purposes, surfacing Salesforce insights via natural language.
• Automated Testing and Monitoring
  Leverage Tooling API and Apex REST endpoints to automate testing scenarios, monitor system health, or trigger custom logic in Salesforce.

How to set it up

Windsurf

1. Ensure uvx and the MCP Salesforce connector are installed.

2. Open your Windsurf configuration file (e.g., windsurf_config.json).

3. Add the Salesforce MCP Server under the mcpServers section:

   {
     "mcpServers": {
       "salesforce": {
         "command": "uvx",
         "args": [
           "--from",
           "mcp-salesforce-connector",
           "salesforce"
         ],
         "env": {
           "SALESFORCE_ACCESS_TOKEN": "SALESFORCE_ACCESS_TOKEN",
           "SALESFORCE_INSTANCE_URL": "SALESFORCE_INSTANCE_URL"
         }
       }
     }
   }
   

4. Save the configuration and restart Windsurf.

5. Verify the setup by running a test Salesforce query.

Note: Secure your Salesforce credentials using environment variables, as shown above.

Claude

1. Install uvx and ensure the MCP Salesforce connector is available.

2. Edit claude_desktop_config.json.

3. Add the following under mcpServers:

   {
     "mcpServers": {
       "salesforce": {
         "command": "uvx",
         "args": [
           "--from",
           "mcp-salesforce-connector",
           "salesforce"
         ],
         "env": {
           "SALESFORCE_ACCESS_TOKEN": "SALESFORCE_ACCESS_TOKEN",
           "SALESFORCE_INSTANCE_URL": "SALESFORCE_INSTANCE_URL"
         }
       }
     }
   }
   

4. Save changes and restart Claude.

5. Run a SOQL query to confirm the server is connected.

Note: Use environment variables for Salesforce credentials as shown.

Cursor

1. Install uvx and the Salesforce MCP connector.

2. Access the Cursor MCP configuration file.

3. Add the Salesforce server in the mcpServers section:

   {
     "mcpServers": {
       "salesforce": {
         "command": "uvx",
         "args": [
           "--from",
           "mcp-salesforce-connector",
           "salesforce"
         ],
         "env": {
           "SALESFORCE_ACCESS_TOKEN": "SALESFORCE_ACCESS_TOKEN",
           "SALESFORCE_INSTANCE_URL": "SALESFORCE_INSTANCE_URL"
         }
       }
     }
   }
   

4. Save and restart Cursor.

5. Test with a sample Salesforce operation.

Note: Secure API keys using environment variables as above.

Cline

1. Install prerequisites (uvx and connector package).

2. Edit the Cline MCP configuration file.

3. Insert the following configuration:

   {
     "mcpServers": {
       "salesforce": {
         "command": "uvx",
         "args": [
           "--from",
           "mcp-salesforce-connector",
           "salesforce"
         ],
         "env": {
           "SALESFORCE_ACCESS_TOKEN": "SALESFORCE_ACCESS_TOKEN",
           "SALESFORCE_INSTANCE_URL": "SALESFORCE_INSTANCE_URL"
         }
       }
     }
   }
   

4. Restart Cline and ensure the server is active.

5. Verify with a basic Salesforce REST API call.

Note: Always secure credentials using environment variables in the “env” section.

Example: Securing API Keys

{
  "mcpServers": {
    "salesforce": {
      "command": "uvx",
      "args": [
        "--from",
        "mcp-salesforce-connector",
        "salesforce"
      ],
      "env": {
        "SALESFORCE_ACCESS_TOKEN": "your-access-token-here",
        "SALESFORCE_INSTANCE_URL": "https://your-instance.salesforce.com"
      }
    }
  }
}

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

Based on the above tables, the Salesforce MCP Server is well-documented for setup and describes its tools thoroughly, but lacks explicit information on prompt templates, resource primitives, and sampling/roots support. Its developer focus and clear authentication setup make it a strong option, though not fully featured by MCP standards.

MCP Score