Salesforce MCP Server Integration

What does “Salesforce” MCP Server do?

The Salesforce MCP Server is a Model Context Protocol (MCP) implementation that connects AI assistants, such as Claude, with Salesforce. It enables natural language interactions with Salesforce data and metadata, allowing users to query, modify, and manage Salesforce objects and records seamlessly. By exposing Salesforce’s powerful APIs through standard MCP tools, the server empowers AI clients to perform database queries, manage objects, handle Apex code, and automate workflows directly within development environments. Developers benefit from streamlined access to Salesforce resources, enhanced productivity, and the ability to build robust, AI-driven integrations and automations across a variety of platforms.

List of Prompts

No explicit prompt templates are listed in the repository.

List of Resources

No explicit MCP resources are listed in the repository.

List of Tools

• salesforce_search_objects
  Search for standard and custom objects in Salesforce using partial name matches.
• salesforce_describe_object
  Retrieve detailed schema information, including fields, relationships, and picklists for an object.
• salesforce_query_records
  Query records with support for relationships and complex conditions.
• salesforce_aggregate_query
  Perform aggregate queries with GROUP BY, HAVING, and various aggregate functions.
• salesforce_dml_records
  Insert, update, delete, or upsert Salesforce records.
• salesforce_manage_object
  Create and modify custom objects and adjust their properties.
• salesforce_manage_field
  Add or modify custom fields, including relationship fields and access permissions.
• salesforce_manage_field_permissions
  Grant/revoke/read field-level security permissions for specific profiles.
• salesforce_search_all
  Search across multiple Salesforce objects using SOSL queries.
• salesforce_read_apex
  Read Apex classes, list them by pattern, and retrieve their source code and metadata.
• salesforce_write_apex
  Create or update Apex classes, specifying code and API versions.
• salesforce_read_apex_trigger
  Read Apex triggers, list triggers, and retrieve their metadata/source code.
• salesforce_write_apex_trigger
  Create or update Apex triggers for specific objects, specifying events and API versions.
• salesforce_execute_anonymous
  Execute anonymous Apex code and view debug logs and results.

Use Cases of this MCP Server

• Salesforce Database Management
  Perform CRUD operations on Salesforce records, streamline data manipulation, and automate repetitive tasks via AI-driven instructions.
• Schema and Metadata Exploration
  Quickly retrieve object schemas, field details, and relationships to aid in building integrations or understanding complex org structures.
• Advanced Reporting and Aggregation
  Execute aggregate queries to generate summaries, perform analytics, and filter grouped results, supporting business intelligence needs.
• Apex Code and Trigger Management
  Read, create, and update Apex classes or triggers directly from your development environment, speeding up deployment and maintenance cycles.
• Cross-object Search and Data Discovery
  Use SOSL-based search to find information across multiple objects, making it easier to locate records and relationships in large Salesforce orgs.

How to set it up

Windsurf

1. Ensure Node.js is installed on your system.
2. Install the Salesforce MCP Server:
   npm install -g @tsmztech/mcp-server-salesforce@latest
3. Locate your Windsurf configuration file (e.g., windsurf.config.json).
4. Add the Salesforce MCP Server using the following JSON snippet:

   {
     "mcpServers": {
       "salesforce-mcp": {
         "command": "mcp-server-salesforce",
         "args": [],
         "env": {
           "SALESFORCE_CLIENT_ID": "your-client-id",
           "SALESFORCE_CLIENT_SECRET": "your-client-secret",
           "SALESFORCE_USERNAME": "your-username",
           "SALESFORCE_PASSWORD": "your-password",
           "SALESFORCE_TOKEN": "your-security-token"
         }
       }
     }
   }
   

5. Save the file and restart Windsurf.
6. Verify the server is running in the MCP dashboard.

Claude

1. Ensure Node.js is installed.
2. Install the Salesforce MCP Server:
   npm install -g @tsmztech/mcp-server-salesforce@latest
3. Edit your Claude integration configuration file.
4. Add the following to the mcpServers section:

   {
     "mcpServers": {
       "salesforce-mcp": {
         "command": "mcp-server-salesforce",
         "args": [],
         "env": {
           "SALESFORCE_CLIENT_ID": "your-client-id",
           "SALESFORCE_CLIENT_SECRET": "your-client-secret",
           "SALESFORCE_USERNAME": "your-username",
           "SALESFORCE_PASSWORD": "your-password",
           "SALESFORCE_TOKEN": "your-security-token"
         }
       }
     }
   }
   

5. Save and restart Claude.
6. Confirm Salesforce MCP availability in your Claude workspace.

Cursor

1. Install Node.js.
2. Install Salesforce MCP:
   npm install -g @tsmztech/mcp-server-salesforce@latest
3. Open the Cursor configuration file.
4. Add the Salesforce MCP Server as shown:

   {
     "mcpServers": {
       "salesforce-mcp": {
         "command": "mcp-server-salesforce",
         "args": [],
         "env": {
           "SALESFORCE_CLIENT_ID": "your-client-id",
           "SALESFORCE_CLIENT_SECRET": "your-client-secret",
           "SALESFORCE_USERNAME": "your-username",
           "SALESFORCE_PASSWORD": "your-password",
           "SALESFORCE_TOKEN": "your-security-token"
         }
       }
     }
   }
   

5. Save changes and restart Cursor.
6. Test server connectivity in the MCP integrations panel.

Cline

1. Make sure Node.js is installed.
2. Install the package:
   npm install -g @tsmztech/mcp-server-salesforce@latest
3. Find and open your Cline config file.
4. Insert the Salesforce MCP Server:

   {
     "mcpServers": {
       "salesforce-mcp": {
         "command": "mcp-server-salesforce",
         "args": [],
         "env": {
           "SALESFORCE_CLIENT_ID": "your-client-id",
           "SALESFORCE_CLIENT_SECRET": "your-client-secret",
           "SALESFORCE_USERNAME": "your-username",
           "SALESFORCE_PASSWORD": "your-password",
           "SALESFORCE_TOKEN": "your-security-token"
         }
       }
     }
   }
   

5. Save and restart Cline.
6. Check the MCP server status in your tools menu.

Securing API Keys:
Always use environment variables for sensitive credentials. In your configuration, add the necessary fields to the env object as shown above.
To pass additional inputs, you can use:

{
  "mcpServers": {
    "salesforce-mcp": {
      "command": "mcp-server-salesforce",
      "args": [],
      "env": {
        "SALESFORCE_CLIENT_ID": "your-client-id"
      },
      "inputs": {
        "instanceUrl": "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-mcp": {
    "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-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Between these two tables, the Salesforce MCP Server offers excellent tool and setup documentation, but lacks documentation on prompt templates, resources, roots, or sampling. Its core strength is its robust Salesforce tool set and clear setup instructions. Based on this, I’d rate the repository a 7/10 for practical MCP integration and developer usability.

MCP Score