Salesforce Connector MCP Server

Customer Data PlatformsPython

Interact with Salesforce data through SOQL queries and SOSL searches

Available Tools

execute_soql

Execute a SOQL (Salesforce Object Query Language) query to retrieve data from Salesforce

execute_sosl

Execute a SOSL (Salesforce Object Search Language) search to find records in Salesforce

get_object_metadata

Retrieve metadata for a Salesforce object, including its fields and relationships

get_object_fields

Retrieve field information for a specific Salesforce object

get_record

Retrieve a specific record from Salesforce by ID

create_record

Create a new record in Salesforce

update_record

Update an existing record in Salesforce

delete_record

Delete a record from Salesforce

execute_tooling_api

Execute a request to the Salesforce Tooling API

execute_apex_rest

Execute a request to a custom Apex REST endpoint

execute_rest_api

Execute a direct REST API call to Salesforce

The Salesforce Connector provides a seamless integration between large language models and Salesforce data. It enables LLMs to execute SOQL queries, perform SOSL searches, and interact with Salesforce records and metadata directly. With this connector, AI assistants can retrieve, create, update, and delete Salesforce records, access object metadata, and execute Tooling API and Apex REST requests. This makes it an essential tool for developers and business users who want to leverage AI capabilities with their Salesforce instance.

Installation

To install the Salesforce Connector, you'll need to add it to your Model Context Protocol configuration.

First, install the package using a package manager:

pip install mcp-salesforce-connector

Configure the MCP server in your client configuration file (e.g., claude_desktop_config.json):

{
    "mcpServers": {
        "salesforce": {
            "command": "uvx",
            "args": [
                "--from",
                "mcp-salesforce-connector",
                "salesforce"
            ],
            "env": {
                "SALESFORCE_USERNAME": "YOUR_SALESFORCE_USERNAME",
                "SALESFORCE_PASSWORD": "YOUR_SALESFORCE_PASSWORD",
                "SALESFORCE_SECURITY_TOKEN": "YOUR_SALESFORCE_SECURITY_TOKEN"
            }
        }
    }
}

Replace the placeholder values with your actual Salesforce credentials:
- YOUR_SALESFORCE_USERNAME: Your Salesforce account username
- YOUR_SALESFORCE_PASSWORD: Your Salesforce account password
- YOUR_SALESFORCE_SECURITY_TOKEN: Your Salesforce security token

Usage

Once configured, the Salesforce Connector provides several tools that allow AI assistants to interact with your Salesforce data:

SOQL Queries

Use the execute_soql tool to run Salesforce Object Query Language queries:

I need to find all Accounts created in the last 30 days.

SOSL Searches

Use the execute_sosl tool to perform Salesforce Object Search Language searches:

Search for contacts with "Smith" in their name.

Object Metadata

Retrieve metadata about Salesforce objects to understand their structure:

What fields are available on the Lead object?

Record Operations

Create, read, update, and delete Salesforce records:

Create a new Contact with the name "John Doe" and email "john.doe@example.com".

Troubleshooting

If you encounter connection issues:

Verify your Salesforce credentials are correct
Ensure your security token is up to date
Check that your Salesforce user has the appropriate API permissions
Confirm your network allows connections to Salesforce API endpoints

For more detailed information, refer to the GitHub repository.