How to Use the Salesforce Marketing Cloud MCP in Mastra AI

Q: How do I add this MCP Server to Mastra AI?

Install @mastra/mcp and instantiate an MCPClient with your server URL. Call mcpClient.listTools() and spread the results into your agent's tool array. The framework auto-detects whether to use SSE or Streamable HTTP.

Q: Can Mastra AI handle Salesforce Marketing Cloud API limits?

The framework manages failures natively. If a call to sfcampaignperformance fails due to traffic, the built-in workflow engine retries with exponential backoff. Your data pipelines keep running without manual intervention.

Q: Does Mastra AI require human approval for Salesforce Marketing Cloud actions?

You control the execution gates. By enabling requireToolApproval, you force the agent to pause before running sfcreatecampaign. A human reviews the budget and dates before the workflow proceeds.

Build resilient Salesforce Marketing Cloud workflows and automated campaign routing with Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Salesforce Marketing Cloud MCP to Mastra AI

Create your Vinkius account to connect Salesforce Marketing Cloud to Mastra AI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Salesforce Marketing Cloud with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Automate campaign creation workflows in Mastra AI

`sf_create_campaign` acts as the trigger point for your automated marketing operations through this MCP Server. Your agent receives a request to launch a new trade show or public relations initiative. It maps the budget and dates, then executes the creation step. If the API hits a rate limit, Mastra automatically applies exponential backoff. Once the campaign exists, the workflow branches. The agent can immediately call `sf_add_campaign_member` to populate the new initiative with targeted leads, setting their initial status to "Sent".

Build resilient ROI reporting pipelines

`sf_campaign_performance` pulls aggregate metrics across all your marketing channels. Your workflow agent fetches the total leads generated, budgeted costs, and actual spend per campaign type. You can wrap this in a conditional logic tree. If the actual cost exceeds the budgeted cost, the agent triggers an alert. It then uses `sf_search_campaigns` to find the specific underperforming initiatives by name, extracting the exact lead conversion numbers before notifying your team.

Audit member engagement automatically

`sf_campaigns_by_status` grabs all "In Progress" or "Completed" campaigns along with their baseline conversion data. Your Mastra workflow runs this on a schedule to monitor active marketing efforts. The agent digs deeper using `sf_campaign_members`. It retrieves the specific leads and contacts tied to those campaigns. If a contact's status shows they registered but never attended, the workflow engine catches that condition and queues a follow-up action.

Setup guide

Set up Salesforce Marketing Cloud MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Salesforce Marketing Cloud tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "salesforce-marketing-cloud-mcp-client",
  servers: {
    "salesforce-marketing-cloud-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Salesforce Marketing Cloud Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Salesforce Marketing Cloud tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Salesforce Marketing Cloud transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Salesforce. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Salesforce Marketing Cloud now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Salesforce Marketing Cloud MCP in Mastra AI

Install `@mastra/mcp` and instantiate an `MCPClient` with your server URL. Call `mcpClient.listTools()` and spread the results into your agent's tool array. The framework auto-detects whether to use SSE or Streamable HTTP.

The framework manages failures natively. If a call to `sf_campaign_performance` fails due to traffic, the built-in workflow engine retries with exponential backoff. Your data pipelines keep running without manual intervention.

You control the execution gates. By enabling `requireToolApproval`, you force the agent to pause before running `sf_create_campaign`. A human reviews the budget and dates before the workflow proceeds.

Set up a sequential workflow. Step one runs the creation tool to get the new ID. Step two takes that ID and feeds it into the member addition tool, passing either a contact ID or a lead ID.

This MCP Server processes raw contact IDs, lead names, and campaign response dates. Every MCP Server on Vinkius executes in a zero-trust environment. The system drops all network connections outside the designated API endpoints and wipes the container after the workflow completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript