What campaign data can I access?

Search campaigns, view members, track conversions, measure costs and ROI — all grouped by type.

Can I add leads to campaigns?

Yes! Add any Lead or Contact as a campaign member with a specific status.

How is campaign performance measured?

Aggregate metrics: total leads, conversions, actual cost per campaign type. Compare ROI across channels.

Salesforce Marketing Cloud MCP Server for Pydantic AI 6 tools — connect in under 2 minutes

Name: Salesforce Marketing Cloud
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 6 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Salesforce Marketing Cloud through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Salesforce Marketing Cloud "
            "(6 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Salesforce Marketing Cloud?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Salesforce Marketing Cloud MCP Server

Connect Salesforce Marketing to any AI agent.

Pydantic AI validates every Salesforce Marketing Cloud tool response against typed schemas, catching data inconsistencies at build time. Connect 6 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Campaigns — Search, create, and filter by status
Members — View and add leads/contacts to campaigns
Performance — Aggregate metrics by campaign type

The Salesforce Marketing Cloud MCP Server exposes 6 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Salesforce Marketing Cloud to Pydantic AI via MCP

Follow these steps to integrate the Salesforce Marketing Cloud MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 6 tools from Salesforce Marketing Cloud with type-safe schemas

Why Use Pydantic AI with the Salesforce Marketing Cloud MCP Server

Pydantic AI provides unique advantages when paired with Salesforce Marketing Cloud through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Salesforce Marketing Cloud integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Salesforce Marketing Cloud connection logic from agent behavior for testable, maintainable code

Salesforce Marketing Cloud + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Salesforce Marketing Cloud MCP Server delivers measurable value.

Type-safe data pipelines: query Salesforce Marketing Cloud with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Salesforce Marketing Cloud tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Salesforce Marketing Cloud and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Salesforce Marketing Cloud responses and write comprehensive agent tests

Salesforce Marketing Cloud MCP Tools for Pydantic AI (6)

These 6 tools become available when you connect Salesforce Marketing Cloud to Pydantic AI via MCP:

sf_add_campaign_member

Provide campaignId and either contactId OR leadId (not both). Status defaults to "Sent" but can be set to "Responded", "Registered", etc. based on your campaign member statuses. Returns the created membership record. Add a lead or contact to a Salesforce marketing campaign for attribution tracking and engagement measurement

sf_campaign_members

Returns member name, type (Lead or Contact), status (Sent/Responded/etc.), and response date. Use to see who is in a campaign, track engagement, or analyze campaign reach. Essential for campaign ROI and attribution analysis. Get all leads and contacts enrolled in a specific Salesforce campaign with their membership status and response dates

sf_campaign_performance

Returns the number of campaigns, total leads generated, total conversions, total budgeted cost, and actual cost per campaign type. Provides an instant ROI overview across all marketing channels. Use for marketing dashboard, channel-level performance comparison, or budget allocation analysis. Get aggregate marketing campaign performance — campaign counts, total leads, conversions, and costs grouped by campaign type

sf_campaigns_by_status

Returns campaigns with lead/contact counts, budget, and conversion data. Use for questions like "which campaigns are currently running?" or "show completed campaigns with their results." Get Salesforce campaigns filtered by status — Planned, In Progress, Completed, or Aborted — with full metrics

sf_create_campaign

Name is required. Type: Email, Conference, Webinar, Trade Show, Public Relations, Advertisement, Banner Ads, Telemarketing. Status defaults to "Planned". Dates use YYYY-MM-DD. budgetedCost is the planned spend. Returns the created campaign with its Salesforce ID. Create a new marketing campaign in Salesforce with name, type, status, dates, description, and budget

sf_search_campaigns

Returns campaign name, status (Planned/In Progress/Completed/Aborted), type (Email/Conference/Webinar/Advertisement), start/end dates, number of leads generated, contacts converted, budgeted cost, and actual cost. Use when the user asks about marketing initiatives, campaign performance, or budget spend. Search Salesforce marketing campaigns by name to find initiatives with status, type, budget, and lead/contact conversion metrics

Example Prompts for Salesforce Marketing Cloud in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Salesforce Marketing Cloud immediately.

"What is the conversion rate of our Email campaigns?"

"Create a new webinar campaign for Q2 product launch"

"Show me all in-progress campaigns"

Troubleshooting Salesforce Marketing Cloud MCP Server with Pydantic AI

Common issues when connecting Salesforce Marketing Cloud to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Salesforce Marketing Cloud + Pydantic AI FAQ

Common questions about integrating Salesforce Marketing Cloud MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Salesforce Marketing Cloud MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.