Live 52 Actions

Adobe Experience Manager MCP Server
for AI Agents

Connect your AI agent to StackOne's Adobe Experience Manager MCP server and give it 52 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →

Adobe Experience Manager MCP Server

Built by

StackOne

Coverage

52 Agent Actions

Create, read, update, and delete across Adobe Experience Manager — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Adobe Experience Manager MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Adobe Experience Manager 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 Adobe Experience Manager call.

Tools Discovery →

What is the Adobe Experience Manager MCP Server?

A Adobe Experience Manager MCP server lets AI agents read and write Adobe Experience Manager data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Adobe Experience Manager MCP server ships with 52 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Adobe Experience Manager MCP Tools

Every action from Adobe Experience Manager's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Assets

Get Asset
Get the metadata of an asset by its ID via the Assets Author API.
Search Assets
Search for assets based on the provided search criteria.
Delete Asset
Delete an asset by its ID.

Asset Relations

Create Asset Relations
Create new asset relations for an asset.
List Asset Relations
Get the asset relations for an asset (paginated, cursor-based).

Requests

Create Batch Request
Submit a batch of AEM Sites API requests in one call.
List Batch Requests
List previously submitted batch requests (paginated, cursor-based).

Content Fragment Models

Create Content Fragment Model
Create one or more Content Fragment Models in a configuration folder.
Publish Content Fragment Models
Publish a set of Content Fragment Models.
List Content Fragment Models
List all Content Fragment Models on the author tier (paginated, cursor-based).
Get Content Fragment Model
Get a single Content Fragment Model by ID.
Search Content Fragment Models
Search Content Fragment Models using filter and sort criteria (paginated, cursor-based).
Update Content Fragment Model
Edit a Content Fragment Model using JSON Patch operations (RFC 6902).
Delete Content Fragment Model
Delete a Content Fragment Model by ID.

Content Fragments

Create Content Fragment
Create a new Content Fragment from a model in a folder.
Publish Content Fragments
Publish a set of Content Fragments by ID or path.
List Content Fragments
List all Content Fragments on the author tier (paginated, cursor-based).
Get Content Fragment
Get a single Content Fragment by ID from the author tier.
Search Content Fragments
Search Content Fragments using filter and sort criteria (paginated, cursor-based).
Update Content Fragment
Edit a Content Fragment using JSON Patch operations (RFC 6902).
Delete Content Fragment
Delete a Content Fragment by ID.

Delivery Content Fragments

List Delivery Content Fragments
List Content Fragments on the publish (delivery) tier with cursor pagination.
Get Delivery Content Fragment
Get a single Content Fragment from the publish (delivery) tier by ID or base64url path.

Folders

Create Folders
Create one or more new folders at the specified DAM paths in AEM.
Delete Folder
Delete a single folder by its ID.

Other (27)

Get Asset Renditions
List the static renditions of an asset.
Get Asset Metadata
Get the metadata document for the specified asset on the author tier.
Get Asset (Delivery)
Get a web-optimized binary representation of the asset from the publish tier.
Get Asset Renditions (Delivery)
List the static renditions of an asset from the publish tier.
Get Asset Metadata (Delivery)
Get the metadata document for the specified asset on the publish tier.
Get Fragments Domain
Get the AEM tier domain URL for the current environment.
Get Delivery Content Fragment References
Get the references of a Content Fragment on the delivery tier.
List Delivery Content Fragment Referenced By
List the parent references (incoming) of a delivery Content Fragment (paginated, cursor-based).
List Delivery Content Fragment Variations
List all variations of a Content Fragment on the delivery tier (paginated, cursor-based).
Get Delivery Content Fragment By Path
Get a Content Fragment from the delivery tier by JCR path.
Get Delivery Content Fragment Model
Get the model details of a Content Fragment on the delivery tier.
Get Fragments Permissions
Get the current user's permissions for a list of Content Fragments or Models.
Get Content Fragments Scheduled Publication Status
Get the scheduled publication status for a list of Content Fragment IDs.
Get Fragments Referenced By
Get the parent references of a list of Content Fragment resources.
Get Fragments Translations
Get the locales and language copies for a list of Content Fragment paths.
Get Fragments Languages
Get the available languages for creating Language Copies of a Content Fragment.
List Launch Jobs
List jobs associated with a Launch (paginated, cursor-based).
Get Content Fragment Models Scheduled Publication Status
Get the scheduled publication status for a list of Content Fragment Model IDs.
List Workflows
List workflows on the author tier (paginated, cursor-based).
Delete Folders By Path
Delete one or more folders identified by their JCR paths.
Find And Replace In Content Fragments
Find and replace text across the text fields of selected Content Fragments.
GraphQL Query (POST)
Execute a GraphQL query against AEM Sites via POST.
GraphQL Query (GET)
Execute a GraphQL query against AEM Sites via GET.
Promote Launch
Promote a Launch into its target.
Rebase Launch
Rebase a Launch against its target.
Bind Metadata Schema
Bind (or unbind) a metadata schema to a resource.
Start Workflow
Start a workflow instance.

Set Up Your Adobe Experience Manager MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Adobe Experience Manager in under 10 lines of code.

MCP Clients

Agent Frameworks

Claude Desktop-

JSON

Claude Desktop Docs

{
  "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>"
      ]
    }
  }
}

Platform 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

MCP vs A2A: Architecture, Security, and When to Use Each

MCP vs A2A: what each protocol standardizes, how they differ, their shared security risks including indirect prompt injection, and when to use one, both, or a hybrid architecture.

12 min

MCP vs API: What 200+ Connector Builds Taught Us

MCP wraps APIs, it doesn't replace them. After building 200+ connectors that serve both, here's when each approach wins.

14 min read

Adobe Experience Manager MCP Server FAQ

Does StackOne have a Adobe Experience Manager MCP server?

Yes. StackOne offers a hosted Adobe Experience Manager MCP server with 52 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.

Adobe Experience Manager MCP server vs direct API integration — what's the difference?

A Adobe Experience Manager MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Adobe Experience Manager. A Adobe Experience Manager 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 Adobe Experience Manager at runtime. StackOne provides both.

How does Adobe Experience Manager authentication work for AI agents?

Adobe Experience Manager 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 Adobe Experience Manager account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.

Are Adobe Experience Manager MCP tools vulnerable to prompt injection?

Yes — Adobe Experience Manager 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 Adobe Experience Manager agent and how do I avoid it?

Context bloat happens when Adobe Experience Manager tool schemas and API responses eat your Adobe Experience Manager agent's memory, preventing it from reasoning effectively. A single Adobe Experience Manager 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 Adobe Experience Manager agent can access?

Yes — you can limit which actions your Adobe Experience Manager 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 Adobe Experience Manager MCP server?

Yes — you can create custom agent actions for your Adobe Experience Manager MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Adobe Experience Manager's API, generate production-ready connector YAML, test against the live API, and validate before you ship.

When should I NOT use a Adobe Experience Manager MCP server?

Skip a Adobe Experience Manager MCP server if your integration is purely software-to-software — direct Adobe Experience Manager 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 Adobe Experience Manager actions at runtime.

What AI frameworks and AI clients does the StackOne Adobe Experience Manager MCP server support?

The StackOne Adobe Experience Manager 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.

Start Free Book Demo

Adobe Experience Manager MCP Serverfor AI Agents