Salesforce CLI

by codefriar

24 stars
345 downloads
Not rated
GitHub

About

Exposes Salesforce CLI functionality for interacting with Salesforce orgs, enabling developers to query data, deploy code, and manage orgs through dynamically discovered commands.

Details

Author
codefriar
Repository
codefriar/sf-mcp
GitHub stars
24
Downloads
345
Categories
AI, Developer Tools, Search, Infrastructure, Project Management

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Salesforce CLI
    Command (node, npx, python, etc.) /path/to/node
    Arguments
    • Argument 1 /path/to/sf-mcp/build/index.js
    • Argument 2 /path/to/project1
    • Argument 3 /path/to/project2

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

npm install


npm start

To configure this MCP in Claude Desktop's .claude.json configuration:

json
{
"tools": {
"salesforce": {
"command": "/path/to/node",
"args": [
"/path/to/sf-mcp/build/index.js",
"/path/to/project1",
"/path/to/project2"
]
}
}
}

Using the npm package directly:

json
{
"tools": {
"salesforce": {
"command": "/path/to/npx",
"args": [
"-y",
"codefriar/sf-mcp",
"/path/to/project1",
"/path/to/project2"
]
}
}
}

Method 1: Via Command Line Arguments
bash

sf_list_roots

sf_version

Get the Salesforce CLI version information

sf_help

Get help information for Salesforce CLI commands

sf_cache_clear

Clear the command discovery cache

sf_cache_refresh

Refresh the command discovery cache

sf_set_project_directory

Set a Salesforce project directory to use for commands. Parameters: directory (path to a directory containing a sfdx-project.json file), name (optional name for this project root), description (optional description for this project root), isDefault (optional set this root as the default for command execution)

sf_list_roots

List all configured project roots

sf_detect_project_directory

Attempt to detect project directory from user messages

sf_org_list

List Salesforce orgs. Parameters: json, verbose

sf_auth_list_orgs

List authenticated Salesforce orgs. Parameters: json, verbose

sf_org_display

Display details about an org. Parameters: targetusername, json

sf_org_open

Open an org in the browser. Parameters: targetusername, path, urlonly

sf_apex_run

Run anonymous Apex code. Parameters: targetusername, file, apexcode, json

sf_apex_test_run

Run Apex tests. Parameters: targetusername, testnames, suitenames, classnames, json

sf_data_query

Execute a SOQL query. Parameters: targetusername, query, json

sf_schema_list_objects

List sObjects in the org. Parameters: targetusername, json

sf_schema_describe

Describe a Salesforce object. Parameters: targetusername, sobject, json

sf_project_deploy_start

Deploy the source to an org. Parameters: targetusername, sourcedir, json, wait

This MCP server provides Salesforce CLI commands as MCP tools. It automatically discovers and registers all available commands from the Salesforce CLI, and also specifically implements the most commonly used commands.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "salesforce cli": {
            "env": {},
            "args": [
                "/path/to/sf-mcp/build/index.js",
                "/path/to/project1",
                "/path/to/project2"
            ],
            "shell": false,
            "command": "/path/to/node"
        }
    }
}

Linux

{
    "env": [],
    "args": [
        "/path/to/sf-mcp/build/index.js",
        "/path/to/project1",
        "/path/to/project2"
    ],
    "shell": false,
    "command": "/path/to/node"
}

Macos

{
    "env": [],
    "args": [
        "/path/to/sf-mcp/build/index.js",
        "/path/to/project1",
        "/path/to/project2"
    ],
    "shell": false,
    "command": "/path/to/node"
}

Windows

{
    "env": [],
    "args": [
        "/c",
        "/path/to/npx",
        "-y",
        "codefriar/sf-mcp",
        "/path/to/project1",
        "/path/to/project2"
    ],
    "shell": true,
    "command": "cmd"
}

Salesforce CLI MCP Server

Model Context Protocol (MCP) server for providing Salesforce CLI functionality to LLM tools like Claude Desktop.

Overview

This MCP server wraps the Salesforce CLI (sf) command-line tool and exposes its commands as MCP tools and resources, allowing LLM-powered agents to:

- View help information about Salesforce CLI topics and commands
- Execute Salesforce CLI commands with appropriate parameters
- Leverage Salesforce CLI capabilities in AI workflows

Requirements

- Node.js 18+ and npm
- Salesforce CLI (sf) installed and configured
- Your Salesforce org credentials configured in the CLI

Installation

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.