▌BestMCPTools.org
Salesforce MCP logo

Salesforce MCP

Connect AI agents to Salesforce CRM records

CRMFreeClaudeCursorVS CodeModerate✓ Verified
Visit Tool

Last verified: August 3, 2026

Own Salesforce MCP? Boost it to the top.✦ Upgrade to Featured

How to Install Salesforce MCP

$npx -y @salesforce/mcp

Compatible with: Claude, Cursor, VS Code.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "salesforce-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@salesforce/mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "salesforce-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@salesforce/mcp"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "salesforce-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@salesforce/mcp"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add salesforce-mcp -- npx -y @salesforce/mcp

Add any API keys or environment variables the server's README lists.

About Salesforce MCP

An MCP server that exposes Salesforce CRM operations (searching accounts and contacts, creating and updating opportunities, and logging tasks) as tools AI agents can call with OAuth-scoped access. Smaller teams on HubSpot can use the HubSpot MCP setup for the same CRM work.

Salesforce MCP is a CRM MCP server designed for developers and AI power users. It enables extending AI assistants with real-world capabilities by exposing a structured set of tools over the Model Context Protocol. Key capabilities include standards-based mcp server interface, works with claude, gpt, gemini, and other mcp clients, tool discovery and structured outputs, and structured tool calls that work cleanly inside an LLM context. It integrates with Claude Desktop, Cursor, Windsurf, and any MCP-compatible client, and is best suited for developers and AI power users who need ai engineers wiring assistants into real tools.

Key Features

  • crm
  • salesforce
  • sales
  • Standards-based MCP server interface
  • Works with Claude, GPT, Gemini, and other MCP clients
  • Tool discovery and structured outputs

Pricing

Free: from Free with Salesforce plan

Pros & Cons

Pros

  • Drop-in support across MCP-compatible AI clients
  • Reduces prompt boilerplate by exposing concrete tool calls
  • Active community and ongoing updates

Cons

  • Requires an MCP-capable client to use
  • Initial setup can require configuration
  • Capability surface depends on what the underlying service exposes

Best For

  • AI engineers wiring assistants into real tools
  • Teams adopting MCP as an integration standard
  • Power users who want more than chat

Our Take on Salesforce MCP

The most direct way to give an AI agent hands-on access to Salesforce pipeline data.

Frequently Asked Questions

Tags

#crm#salesforce#sales