How to Use the Salesforce Marketing Cloud MCP in AutoGen

Let your AutoGen agents debate campaign strategy using real-time Salesforce Marketing Cloud data as their source of truth.

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 AutoGen

Create your Vinkius account to connect Salesforce Marketing Cloud to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Negotiate campaign budgets via multi-agent debate

Task your performance agent with analyzing `sf_campaign_performance` while your planning agent drafts new initiatives. They debate the ROI, ensuring every `sf_create_campaign` call is backed by data-driven consensus. This prevents impulsive spending. Your agents challenge each other's assumptions, forcing the system to justify every marketing dollar before it commits to a new campaign status.

Resolve campaign status conflicts with logic

When your team needs to know which initiatives are active, your agents call `sf_campaigns_by_status`. If the data shows underperformance, one agent suggests pausing while another proposes a pivot. You get a decision-making system that weighs multiple perspectives. It turns raw Salesforce Marketing Cloud status reports into actionable, debated marketing strategies.

Track member engagement through agent consensus

Your agents verify lead and contact engagement by querying `sf_campaign_members`. They collaborate to identify which segments respond best, then decide whether to add more members using `sf_add_campaign_member`. This removes the bias of a single agent. By requiring consensus, your AutoGen setup ensures your campaign member lists are managed with high precision and shared accountability.

Setup guide

Set up Salesforce Marketing Cloud MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Salesforce Marketing Cloud tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Salesforce Marketing Cloud_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Salesforce Marketing Cloud data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Salesforce Marketing Cloud_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Salesforce Marketing Cloud data")
    print(result.messages[-1].content)

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 AutoGen

You provide the tools to your AssistantAgent. The agents then call `sf_search_campaigns` or other tools whenever they need fresh data to support their debate.

Yes. You set up a group chat where agents must reach consensus before executing any modification tool, ensuring all campaign updates are reviewed by your team's logic.

Your agents can include a 'compliance' persona that monitors call frequency and ensures the team stays within your Salesforce API rate limits during their discussions.

Your agents will flag the inconsistency. Because they communicate, one agent can alert the others to the data anomaly, preventing faulty decisions based on bad metrics.

The server operates under strict zero-trust principles. Only the specific campaign records your agents explicitly request are ever processed, ensuring your private marketing data stays locked down.

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