Log inSubmit server
Salesforce Cloud logo

Salesforce Cloud

Connects AI assistants to Salesforce for SOQL queries, CRM operations, opportunity analysis, and business document generation.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Salesforce Cloud

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "salesforce-cloud": {
      "command": "npx",
      "args": [
        "-y",
        "@aaronsb/salesforce-cloud-mcp"
      ],
      "env": {
        "SF_CLIENT_ID": "YOUR_VALUE_HERE",
        "SF_CLIENT_SECRET": "YOUR_VALUE_HERE",
        "SF_USERNAME": "YOUR_VALUE_HERE",
        "SF_PASSWORD": "YOUR_VALUE_HERE",
        "SF_LOGIN_URL": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @aaronsb/salesforce-cloud-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 21d ago.

Overview

Salesforce Cloud MCP server connects AI assistants to Salesforce data and operations through the Model Context Protocol. It supports opportunity search, SOQL queries, standard CRUD workflows, engagement analysis, pipeline insights, and business case document generation. Use it when an agent needs to inspect Salesforce records, analyze sales activity, or work with organization-specific fields. The server runs through Node.js and authenticates with Salesforce connected-app credentials.

Use cases

  • Search Salesforce opportunities by account, amount, stage, or participant
  • Analyze engagement across calls, emails, and activities
  • Compare open deals with similar won opportunities
  • Inspect custom Salesforce fields before writing SOQL
  • Generate business cases and executive summaries

Key features

  • SOQL querying
  • Opportunity and account search
  • Standard Salesforce CRUD operations
  • Custom-field discovery
  • Engagement and pipeline analysis
  • PDF business case generation

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

11/15 checks healthy over the last 91d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · @aaronsb/salesforce-cloud-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars6Stargazers on the source repository.
npm downloads260Package downloads in the last 30 days.
Last commit2mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Salesforce Cloud works

What Salesforce Cloud does

Salesforce Cloud MCP server exposes Salesforce CRM data and operations to AI assistants through MCP. It is designed for sales workflows that combine record access with analysis, including finding opportunities, reviewing account information, examining engagement activity, and comparing current deals with previously won opportunities.

The server supports natural-language requests that can be translated into Salesforce searches or SOQL queries. It also provides standard CRUD operations for Salesforce data, pagination for larger result sets, and response structures intended for AI workflows. The repository description additionally identifies file downloads and analytics as supported use cases.

Analytical workflows include opportunity intelligence, conversation and engagement analysis, pipeline evaluation, performance analysis, and recommendations based on similar successful deals.

How it works

The MCP server runs as a Node.js process and gives a compatible AI client access to Salesforce through configured tools. A user can ask for records using business terms such as an account, opportunity stage, amount, or involved employee. The assistant then searches Salesforce or constructs a SOQL query for the requested information.

Salesforce Cloud MCP server includes field-discovery guidance for organizations that use custom Salesforce fields. Custom fields commonly end in __c, but their names vary by Salesforce org. The describe_object tool can inspect an object and return its fields when includeFields is enabled. The search_fields tool helps locate fields when the API name is unknown. Field metadata can then be used to form a query against standard or custom fields.

Pagination is available for result sets that exceed a single response. This is relevant when searching broad opportunity, account, activity, or other Salesforce data collections.

Setup and configuration

Install the package with npx @aaronsb/salesforce-cloud-mcp, install it globally with npm, or build the repository from source with npm install, npm run build, and node build/index.js.

The configuration example is for Claude Desktop and starts the server with Node. Add the server under the client’s mcpServers object, then provide the Salesforce credentials as environment variables. The README gives separate configuration paths for Linux and macOS Claude Desktop installations.

Salesforce Cloud MCP server uses a Salesforce Connected App for authentication. Create the app in Salesforce Setup through App Manager, enable OAuth, add the required scopes, and use its Consumer Key and Consumer Secret as the client credentials. SF_LOGIN_URL defaults to https://login.salesforce.com when it is not set.

Tools and capabilities

  • Search opportunities, accounts, and other Salesforce records.
  • Run SOQL queries against Salesforce data.
  • Inspect object metadata and discover standard or custom fields.
  • Create, read, update, and delete Salesforce records.
  • Analyze engagement, pipeline patterns, and similar won opportunities.
  • Generate business cases and executive summaries as PDFs.
  • Retrieve files and handle paginated responses.

Limitations and notes

Field names and available objects depend on the connected Salesforce org. A label shown in Salesforce’s user interface may map to a different API name, especially for custom fields. Inspect object metadata before querying unfamiliar fields or constructing queries that depend on organization-specific schema.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Salesforce Cloud

Salesforce Cloud is an MCP server that connects AI assistants to Salesforce through OAuth credentials from a Connected App. Its main tools support record search, SOQL queries, standard CRUD operations, object-field discovery, opportunity and engagement analysis, and generation of business case or executive-summary PDFs.

Install it with npx, install the npm package globally, or build it from source. The documented options are `npx @aaronsb/salesforce-cloud-mcp`, `npm install -g @aaronsb/salesforce-cloud-mcp`, or cloning the repository and running `npm install`, `npm run build`, and `node build/index.js`.

Configure a Salesforce Connected App and provide its OAuth client ID and secret, Salesforce username and password, and login URL as environment variables. Create the app in Salesforce Setup under App Manager, enable OAuth, add scopes, and use the generated Consumer Key and Consumer Secret.

Inspect the object metadata before querying custom fields. Use `describe_object` with `includeFields: true` or use `search_fields` to find the API name, then construct the SOQL query with the discovered field, which often ends in `__c`.

Yes, Claude Desktop is the documented client configuration. Add the server to its `mcpServers` configuration, set the Node command and server path, and provide the Salesforce environment variables.

Related MCP servers

All in Customer Data Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSalesforce Cloud AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/salesforce-cloud?style=directory)](https://allmcps.com/mcp/salesforce-cloud)
HTML Embed
<a href="https://allmcps.com/mcp/salesforce-cloud"><img src="https://allmcps.com/api/badge/salesforce-cloud?style=directory" alt="Salesforce Cloud on AllMCPs" /></a>