ESC

AI-powered search across all blog posts and tools

AI · April 2, 2026

Salesforce MCP Servers Explained - Your 2026 Field Guide

Salesforce now ships three different flavours of Model Context Protocol support — DX MCP Server, Hosted MCP Servers, and the Agentforce MCP Client. Here's how they fit together and which one you should reach for first.

☕ 9 min read 📅 April 2, 2026
  • Salesforce supports MCP in three different places — DX MCP Server, Hosted MCP Servers, and Agentforce as an MCP Client
  • DX MCP Server runs locally via npx and is for developers using Claude Code, Cursor, or VS Code
  • Hosted MCP Servers run on Salesforce infrastructure and expose sObject, Tableau, Data Cloud, and Revenue Cloud tools over OAuth
  • Agentforce 360 consumes MCP servers with a trusted gateway, allowlist, and enterprise policy enforcement
  • Pick the surface based on who the caller is — a human in an IDE, a backend service, or an autonomous agent

Model Context Protocol (MCP) is the open standard that finally gives large language models a stable way to call tools, read data, and trigger actions across different systems. Think of it as the “USB-C port” for AI assistants — one plug, many devices.

Salesforce has been leaning into MCP hard. As of April 2026, there are three different MCP surfaces shipping across the platform, and they all do different things. If you’ve been confused by the marketing, you’re not alone — I had to draw this map for myself before I understood the boundaries.

Here’s the one I wish I’d had a month ago.

The Three MCP Surfaces in Salesforce

Where MCP Lives Inside Salesforce Today
Salesforce + MCP — Three Surfaces, Three AudiencesDX MCP ServerRuns locally (npx)For: DevelopersClaude Code, Cursor,VS Code, ClineDoes:Deploy / retrieve metadataSOQL, Apex tests, scratch orgs60+ tools across 14 toolsetsHosted MCP ServersRuns in Salesforce (Beta)For: Integrations / TeamsAny MCP client overOAuth + mcp-remoteDoes:sObject CRUD, SOQL / SOSLTableau, Data CloudRevenue Lifecycle MgmtAgentforce MCP ClientInside Agentforce 360For: Autonomous AgentsCalls external orinternal MCP serversAdds:Trusted gateway + allowlistServer registryPolicy enforcementHuman in IDE → DX | Backend / partner → Hosted | Agent → Agentforce Client

The short version: who is doing the calling decides which surface you use.

  • A human engineer in an IDE talking to their org → DX MCP Server
  • A backend service, partner system, or analyst tool that needs a stable, hosted endpoint → Hosted MCP Servers
  • An autonomous Agentforce agent that needs to reach out to registered tools → Agentforce MCP Client

Let me unpack each.

1. Salesforce DX MCP Server

This is the one most developers meet first. It’s a Node-based MCP server you install locally — npx -y @salesforce/mcp — that exposes around 60 Salesforce tools through any MCP-aware client.

It is currently marked as pilot / beta under Salesforce’s Beta Services Terms, and it talks to orgs you’ve already authorized with sf org login web.

ℹ️ Who this is for

If you spend your day in Claude Code, Cursor, VS Code, or Cline and you want your AI assistant to deploy metadata, run SOQL, execute anonymous Apex, run tests, and spin up scratch orgs on your behalf — this is the one.

The 14 toolsets bundle tools by intent — orgs, metadata, data, users, testing, code-analysis, lwc-experts, aura-experts, devops, and more. You opt in to only the ones you need via the --toolsets flag, which is both a security practice (fewer tools = smaller blast radius) and a context-window practice (fewer tools = less prompt bloat for the model).

{
  "mcpServers": {
    "Salesforce DX": {
      "command": "npx",
      "args": [
        "-y", "@salesforce/mcp",
        "--orgs", "DEFAULT_TARGET_ORG",
        "--toolsets", "orgs,metadata,data,users"
      ]
    }
  }
}

I walk through the full setup — including the pitfalls around ALLOW_ALL_ORGS and --allow-non-ga-tools — in the DX MCP setup guide.

2. Salesforce Hosted MCP Servers (Beta)

This is the one that will matter most to business teams over the next 12 months.

Hosted MCP Servers run on Salesforce’s own infrastructure. You don’t install anything locally — you point an MCP client at a URL, go through OAuth, and the client gets a curated set of MCP tools that wrap Salesforce APIs. They entered Beta in late 2025 and are targeted for GA in 2026.

What the beta currently exposes:

  • Core Platform — sObject CRUD, SOQL / SOSL, schema discovery, basic developer tooling
  • Tableau / Tableau Next — semantic models, dashboards, natural-language data analysis
  • Data Cloud — query Data Cloud entities with SQL
  • Revenue Lifecycle Management — quoting, ordering, configuration, pricing engine
💡 Why this matters for non-developers

Hosted MCP Servers let any MCP-speaking tool — Claude.ai, ChatGPT desktop, an internal assistant, a partner agent — hit real Salesforce data and workflows without you writing a single line of integration code. OAuth, rate limits, and audit are Salesforce’s problem, not yours.

I cover the business side of this in Hosted MCP Servers for business teams.

3. Agentforce as an MCP Client

The third surface is the one people get most confused about: Agentforce itself is an MCP client.

In other words, your Agentforce agents — the ones you’re building on Atlas Reasoning Engine with topics, actions, and guardrails — can be pointed at any MCP-compliant server (Salesforce’s own Hosted servers, Heroku, MuleSoft, AWS, Box, Google Cloud, IBM, Notion, PayPal, Stripe, and a growing list of partners). The agent gets new tools without you writing invocable Apex.

⚠️ Don't let an agent talk to the open internet

Agentforce 360 layers a trusted gateway, MCP server registry, and allowlist on top of the raw MCP protocol. This is deliberately zero-trust — admins decide which servers are reachable and which tools are callable. If you turn this off or open it up, you’ve just signed up for tool-poisoning attacks. Don’t.

When to Use Which

Decision Flow — Which MCP Surface?
Pick by Caller, Not by FeatureWho is making the call?(human / integration / agent)Developer in an IDENeeds local dev tools,deploys, tests, SOQL→ DX MCP ServerBackend / partner toolNeeds stable endpoint,OAuth, governed data→ Hosted MCP ServerAutonomous agentReaches out to manygoverned tools + servers→ Agentforce MCP ClientYou can (and often will) use more than one.They're complements, not alternatives.

A real-world architecture I’m seeing take shape at clients looks like this:

  1. Engineers use DX MCP Server locally to move faster on day-to-day dev
  2. An Agentforce service agent talks to internal Salesforce data via the Hosted MCP Server and to a partner system (say, Stripe) via the Agentforce MCP Client
  3. The MCP server registry inside Agentforce keeps the whole thing auditable

No one layer is doing everything. That’s the point.

What About Security?

The three things to check before you roll any of this out

1. Allowlist, not open internet. For Agentforce, keep the registry tight. Only servers that have been reviewed by your security team should be reachable. Salesforce’s default posture here is zero-trust — don’t weaken it.

2. Least-privileged toolsets. For the DX server, use --toolsets aggressively. Don’t ship developers a config that enables all 14 toolsets “just in case”. More tools mean more prompt-injection surface.

3. OAuth scopes. For Hosted MCP Servers, the connected app scopes are the real control. Treat them like you’d treat an integration user — the agent is an integration user.

🚨 Real-World Scenario

Problem: A team wired their Claude Code setup to the DX MCP Server with --orgs ALLOW_ALL_ORGS and shared the config across the team. A developer accidentally ran “deploy this” against production because Claude picked the first matching alias.

Fix: Always scope to a specific alias or DEFAULT_TARGET_ORG in dev environments, and keep production orgs out of the MCP surface entirely — or at minimum, behind a second explicit alias that can’t be confused with a sandbox.

What’s Coming Next

The roadmap that has been publicly signalled:

  • Hosted MCP Servers — GA targeted in 2026, with custom MCP server configurations for specific business needs
  • Agentforce MCP Client — broader GA coverage across regions, deeper registry integration
  • Partner ecosystem — 30+ launch partners committed to listing MCP servers, including AWS, Box, Cisco, Google Cloud, IBM, Notion, PayPal, Stripe, Teradata, and WRITER

If you’re planning your AI integration strategy for the next 12 months, assume MCP is the integration protocol, the same way REST became the integration protocol a decade ago.


A backend analytics service needs to query Data Cloud via natural language from an internal AI assistant. Which Salesforce MCP surface should it use?
Why does Agentforce layer a trusted gateway and allowlist on top of MCP?

If you’re currently evaluating MCP for your org, which of the three surfaces do you think you’ll reach for first — and is there a part of the picture you’re still unsure about?

How did this article make you feel?

Comments

Salesforce Tip

🎉

You finished this article!

What to read next

Contents