Salesforce Connector

@smn2gnton 13 days ago

85 MIT

FreeCommunity

Productivity

#salesforce

Interact with Salesforce Data and Metadata

run_soql_query

Executes a SOQL query against Salesforce

run_sosl_search

Executes a SOSL search against Salesforce

get_object_fields

Retrieves field Names, labels and types for a specific Salesforce object

get_record

Retrieves a specific record by ID

create_record

Creates a new record

update_record

Updates an existing record

delete_record

Deletes a record

tooling_execute

Executes a Tooling API request

apex_execute

Executes an Apex REST request

restful

Makes a direct REST API call to Salesforce

Overview

What is Salesforce Connector

The MCP Salesforce Connector is a server implementation designed to facilitate integration between language models (LLMs) and Salesforce data through the Model Context Protocol (MCP). It enables executing queries and commands specifically tailored for Salesforce environments, allowing for efficient data retrieval and manipulation.

Use cases

Use cases for the MCP Salesforce Connector include querying Salesforce databases for specific records using SOQL, performing broad searches with SOSL, managing Salesforce records (including creating, updating, and deleting), retrieving Salesforce object metadata, and integrating custom functionalities via Apex REST and Tooling API requests.

How to use

To utilize the MCP Salesforce Connector, update your ‘claude_desktop_config.json’ file by adding the necessary configuration details under the ‘mcpServers’ section. Set the environment variables for Salesforce authentication, either using OAuth with ‘SALESFORCE_ACCESS_TOKEN’ and ‘SALESFORCE_INSTANCE_URL’, or fallback to username and password authentication if OAuth is not configured.

Key features

Key features include executing SOQL queries, performing SOSL searches, retrieving Salesforce object metadata, CRUD operations on Salesforce records, executing Tooling API requests, executing Apex REST requests, and making direct REST API calls to Salesforce.

Where to use

This connector is ideal for use cases involving Salesforce data manipulation and retrieval in applications where LLMs need to interact with Salesforce environments, such as customer support platforms, data analytics tools, or integration middleware that facilitates communication between Salesforce and other systems.

Content

MCP Salesforce Connector

A Model Context Protocol (MCP) server implementation for Salesforce integration, allowing LLMs to interact with Salesforce data through SOQL queries and SOSL searches.

Features

Execute SOQL (Salesforce Object Query Language) queries
Perform SOSL (Salesforce Object Search Language) searches
Retrieve metadata for Salesforce objects, including field names, labels, and types
Retrieve, create, update, and delete records
Execute Tooling API requests
Execute Apex REST requests
Make direct REST API calls to Salesforce

Configuration

Model Context Protocol

To use this server with the Model Context Protocol, you need to configure it in your claude_desktop_config.json file. Add the following entry to 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",
            }
        }
    }
}

Note on Salesforce Authentication Methods

This server supports two authentication methods:

OAuth (Recommended): Set SALESFORCE_ACCESS_TOKEN and SALESFORCE_INSTANCE_URL as environment variables.
Username/Password (Legacy): If SALESFORCE_ACCESS_TOKEN and SALESFORCE_INSTANCE_URL are not set, the server will fall back to using SALESFORCE_USERNAME, SALESFORCE_PASSWORD, and SALESFORCE_SECURITY_TOKEN.

Tools