salesforcecli/mcp

MCP Server for interacting with Salesforce instances

What it solves

This project provides a way for Large Language Models (LLMs) to interact directly with Salesforce orgs. It acts as a bridge, allowing AI agents or LLM-powered IDEs to read, manage, and operate Salesforce resources securely without the user having to manually move data between the AI and the platform.

How it works

It implements the Model Context Protocol (MCP), which is a standard for connecting AI models to external data and tools. The server is configured via a JSON file in an MCP-compatible client (like Cursor, Claude Code, or Cline). Once connected, the LLM can call specific "tools" provided by the server to perform actions in Salesforce, such as managing metadata, users, or data.

Who it’s for

Salesforce developers and administrators who use AI-powered coding assistants or agents to automate development, data management, and org configuration.

Highlights

  • Toolsets for Context Management: Includes over 60 tools organized into toolsets (e.g., metadata, data, users, testing) so users can enable only what is needed to avoid overwhelming the LLM's context window.
  • Broad Integration: Compatible with major MCP clients including VS Code Copilot, Claude Code, Cline, Cursor, Trae, Windsurf, and Zed.
  • Secure Org Access: Integrates with locally authorized Salesforce orgs using the Salesforce CLI (sf) authentication flow.
  • Specialized AI Capabilities: Includes expert toolsets for Aura-to-LWC migration, static code analysis, and Apex performance detection.

Related

  • Project
    InditexTech/mcp-teams-server

    An MCP server that integrates Microsoft Teams with LLMs, allowing AI agents to read messages, create threads, and mention members.

  • Project
    korotovsky/slack-mcp-server

    An MCP server that enables AI models to interact with Slack workspaces, allowing them to read, search, and manage messages, users, and channels.

  • Project
    googleapis/mcp-toolbox

    MCP Toolbox is an open‑source server that lets AI agents and IDEs talk to enterprise databases via the Model Context Protocol. It offers ready‑made database tools and a framework for defining custom, secure SQL/semantic‑search tools, with SDKs for Python, JS/TS, Go, and Java.

  • Project
    benborla/mcp-server-mysql

    An MCP server that enables LLMs to inspect MySQL schemas and execute SQL queries, featuring built-in PII redaction and secure remote access.

  • Project
    microsoft/mcp

    A collection of Model Context Protocol (MCP) servers and core tooling that standardizes how AI agents and LLMs connect to Microsoft services and external data sources.