Salesforce logo

Salesforce

Salesforce MCP Pack

Install Salesforce

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-2": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-salesforce"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @pipeworx/mcp-salesforce

initialize succeeded but no response to tools/list.

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 3d ago.

Overview

Tools8

What Salesforce lets your agent do. Expand a tool for its parameters.

Self-reported~293 tokens of context

Security & health

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

ActiveLast checked 2d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · @pipeworx/mcp-salesforce (npm)

Adoption & maintenance

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

npm downloads447Package downloads in the last 30 days.
Last commit27d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed8Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

From the project README

mcp-salesforce

Salesforce MCP Pack

Part of Pipeworx — an MCP gateway connecting AI agents to 1683+ live data sources.

Tools

ToolDescription
sf_queryQuery Salesforce records using SOQL. Returns matching records with all requested fields. Use sf_describe first to learn available fields for your object.
sf_get_recordFetch a single Salesforce record by ID. Specify object type (e.g., 'Account', 'Contact', 'Opportunity') and record ID. Returns all fields.
sf_searchSearch across Salesforce objects by keyword. Returns matching records from multiple object types like Accounts, Contacts, Leads. Use for broad keyword searches.
sf_describeGet schema details for a Salesforce object (e.g., 'Account'). Returns field names, types, relationships, and metadata. Use before querying to understand available fields.
sf_list_objectsList all SObject types available in your Salesforce org. Returns object names and labels. Use to discover queryable objects.
sf_create_recordCreate a new Salesforce record. Specify object type (e.g., 'Contact') and field values. Returns the new record ID.
sf_update_recordUpdate an existing Salesforce record by ID. Specify object type and field values to change. Returns success status.
sf_delete_recordDelete a Salesforce record by ID. Specify object type and record ID. Returns success status.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

config.json
{
  "mcpServers": {
    "salesforce": {
      "url": "https://gateway.pipeworx.io/salesforce/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/salesforce/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

config.json
{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1683+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack runs against a connected salesforce account, so it needs a Pipeworx key: sign in at https://pipeworx.io/account, connect salesforce, then call POST https://gateway.pipeworx.io/v1/tools/salesforce_sf_query with Authorization: Bearer <your Pipeworx key>. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/salesforce_sf_query. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

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

Or run it directly to confirm it starts:

Terminal
npx -y @pipeworx/mcp-salesforce

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

Code
ask_pipeworx({ question: "your question about Salesforce data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT

Reviews

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

Frequently Asked Questions about Salesforce

Salesforce is an MCP server that connects AI agents to Salesforce through tools for querying, searching, describing, creating, updating, and deleting records. It supports SOQL queries, record retrieval by ID, cross-object keyword search, object discovery, and schema inspection. The pack can run through Pipeworx or as a local stdio MCP server.

Use the `sf_query` tool to query Salesforce records with SOQL and return the requested fields. Use `sf_describe` first to inspect the object’s available fields, types, relationships, and metadata before constructing the query.

Use `sf_list_objects` to discover the SObject types available in your Salesforce org, then use `sf_describe` for field names, types, relationships, and metadata for a specific object such as Account or Contact.

Yes, it can create, update, and delete Salesforce records. Use `sf_create_record` with an object type and field values, `sf_update_record` with an object type, record ID, and changed fields, or `sf_delete_record` with an object type and record ID.

Run the standalone server with `npx -y @pipeworx/mcp-salesforce` or configure an MCP client to use that command with the same argument. The local package communicates over stdin/stdout and does not require a Pipeworx account.

Related MCP servers

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 AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/salesforce-2?style=directory)](https://allmcps.com/mcp/salesforce-2)
HTML Embed
<a href="https://allmcps.com/mcp/salesforce-2"><img src="https://allmcps.com/api/badge/salesforce-2?style=directory" alt="Salesforce on AllMCPs" /></a>