Connect
Optimize
Secure
Salesforce Marketing Cloud MCP Server
for AI Agents
Production-ready Salesforce Marketing Cloud MCP server with 50 extensible actions — plus built-in authentication, security, and optimized execution.
Salesforce Marketing Cloud MCP Server
Built by 
StackOne
StackOne 
Coverage
50 Agent Actions
Create, read, update, and delete across Salesforce Marketing Cloud — and extend your agent's capabilities with custom actions.
Authentication
Agent Tool Authentication
Per-user OAuth in one call. Your Salesforce Marketing Cloud MCP server gets session-scoped tokens with zero credentials stored on your infra.
Agent Auth →
Security
Agent Protection
Every Salesforce Marketing Cloud tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.
Prompt Injection Defense →
Performance
Max Agent Context. Min Cost.
Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Salesforce Marketing Cloud call.
Tools Discovery →What is the Salesforce Marketing Cloud MCP Server?
A Salesforce Marketing Cloud MCP server lets AI agents read and write Salesforce Marketing Cloud data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Salesforce Marketing Cloud MCP server ships with 50 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, and optimized agent context. Connect it from MCP clients like Claude Desktop, Cursor, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.
All Salesforce Marketing Cloud MCP Tools and Actions
Every action from Salesforce Marketing Cloud's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.
Assets
- Create Asset
Create a new content asset in Content Builder
- Get Assets
Retrieve a list of content assets from Content Builder
- Get Asset
Retrieve a single content asset by ID
- Delete Asset
Delete a content asset by ID
Asset Categorys
- Create Asset Category
Create a new asset category (folder) in Content Builder
- Get Asset Category
Retrieve a single Content Builder category by ID
- Update Asset Category
Update an existing Content Builder category
- Delete Asset Category
Delete a Content Builder category by ID
Campaigns
- Create Campaign
Create a new campaign
- Get Campaigns
Retrieve a list of campaigns
- Get Campaign
Retrieve a single campaign by ID
- Update Campaign
Update an existing campaign
- Delete Campaign
Delete a campaign by ID
Campaign Assets
- Get Campaign Assets
Retrieve assets associated with a campaign
- Get Campaign Asset
Retrieve a specific asset associated with a campaign
Contact Attribute Groups
- List Contact Attribute Groups
Retrieve all attribute groups for a contact data schema
- Get Contact Attribute Group
Retrieve a specific attribute group for a contact data schema
Contacts
- Create Contact
Create or update a contact
- Search Contacts
Search for contacts using filter criteria
Journeys
- Search Journeys
Retrieve a list of journeys from Journey Builder
- Get Journey
Retrieve a single journey by ID or key
- Delete Journey
Delete a journey by ID or key
Other (28)
- Add Asset To Campaign
Associate one or more assets with a campaign
- Create Custom Data Extension
Create a new data extension using the custom objects API
- Publish Journey Version
Publish a journey asynchronously
- Get Assets Advanced Query
Retrieve assets using an advanced query
- Get Asset File
Retrieve the binary file for an asset by ID
- Get Salutations
Retrieve the default header and footer salutations for the account
- Get Asset Header And Footer
Retrieve the header and footer salutations for a specific asset
- Get Channel View
Retrieve the compiled HTML for a channel view of an asset
- Get Asset Categories
Retrieve a list of Content Builder categories
- Get Audit Events
Retrieve Audit Trail events for the current account and child accounts
- Get Security Events
Retrieve Audit Trail security events for the current account and child accounts
- Get Schemas Collection
Retrieve all contact data schemas for the current account
- Get All Attribute Set Definitions
Retrieve all attribute set definitions from the contact data model
- Get Attribute Set Definition
Retrieve a specific attribute set definition by ID
- Get Contact Membership
Retrieve journeys and versions for a list of contact keys
- Get Contact Preferences
Retrieve consent and privacy preferences for a contact by ID
- Get Contact Preferences By Key
Retrieve consent and privacy preferences for a contact by contact key
- Search Data Extensions
Retrieve a list of data extensions matching a search string
- Get Data Extension By ID
Retrieve a data extension by its unique ID
- Get Data Extension Fields
Retrieve all fields in a data extension
- Get Journey Publish Status
Check the status of an asynchronous journey publication
- Remove Asset From Campaign
Remove the association between an asset and a campaign
- Patch Asset
Patch the properties of a content asset in Content Builder
- Archive Asset
Archive a content asset by ID
- Restore Asset
Restore an archived content asset by ID
- Clear Data Extension Data
Delete all rows from a data extension
- Insert Journey
Create a new journey in Journey Builder
- Stop Journey
Stop a running journey
Set Up Your Salesforce Marketing Cloud MCP Server in Minutes
One endpoint. Any framework. Your agent is talking to Salesforce Marketing Cloud in under 10 lines of code.
MCP Clients
Agent Frameworks
JSON{
"mcpServers": {
"stackone": {
"command": "npx",
"args": [
"-y",
"mcp-remote@latest",
"https://api.stackone.com/mcp?x-account-id=<account_id>",
"--header",
"Authorization: Basic <YOUR_BASE64_TOKEN>"
]
}
}
}More marketing MCP Servers
Kit
53+ actions
Salesforce Marketing Cloud MCP Server Resources
MCP Code Mode: Keeping Tool Responses Out of Agent Context
Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.
11 min
Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery
Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.
10 min
Indirect Prompt Injection Defense for MCP Tools: A Technical Guide
MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.
12 min
Salesforce Marketing Cloud MCP Server FAQ
Salesforce Marketing Cloud MCP server vs direct API integration — what's the difference?
A Salesforce Marketing Cloud MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Salesforce Marketing Cloud. A Salesforce Marketing Cloud MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Salesforce Marketing Cloud at runtime. StackOne provides both.
How does Salesforce Marketing Cloud authentication work for AI agents?
Salesforce Marketing Cloud authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Salesforce Marketing Cloud account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via
origin_owner_id.Are Salesforce Marketing Cloud MCP tools vulnerable to prompt injection?
Yes — Salesforce Marketing Cloud MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Salesforce Marketing Cloud agent and how do I avoid it?
Context bloat happens when Salesforce Marketing Cloud tool schemas and API responses eat your Salesforce Marketing Cloud agent's memory, preventing it from reasoning effectively. A single Salesforce Marketing Cloud query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Salesforce Marketing Cloud agent can access?
Yes — you can limit which actions your Salesforce Marketing Cloud agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Salesforce Marketing Cloud MCP server?
Yes — you can create custom agent actions for your Salesforce Marketing Cloud MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Salesforce Marketing Cloud's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Salesforce Marketing Cloud MCP server?
Skip a Salesforce Marketing Cloud MCP server if your integration is purely software-to-software — direct Salesforce Marketing Cloud API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Salesforce Marketing Cloud actions at runtime.
What AI frameworks and AI clients does the StackOne Salesforce Marketing Cloud MCP server support?
The StackOne Salesforce Marketing Cloud MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.
Put your AI agents to work
All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.