mcpField
S
Salesforce

Salesforce

Remote
pipeworx.ioBusiness & Marketing0Updated 5w ago

About Salesforce

Salesforce MCP Pack exposes Salesforce record discovery and CRUD operations for AI agents working with Salesforce data. It supports both a local stdio server and a Pipeworx gateway endpoint.

Key features

  1. 01SOQL record queries
  2. 02Keyword search across objects
  3. 03Object schema and discovery
  4. 04Fetch, create, update, and delete records

Use cases

  1. 01Inspect an object's fields before querying
  2. 02Find records across Salesforce objects
  3. 03Retrieve or maintain individual Salesforce records

MCP support

Provides Salesforce tools to MCP clients, either through a local stdio server or the Pipeworx gateway. The gateway endpoint also includes shared Pipeworx meta-tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/salesforce/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

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.):

{
  "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:

{
  "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:

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

Or run it directly to confirm it starts:

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:

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

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.