AEM MCP server
✓ VerifiedAllows AI agents to manage Adobe Experience Manager instances using natural language for content, components, assets, and workflows.
Also known as easingthemes/aem-mcp-server
- Stars
- 4
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.3.9
- Last commit
- Jun 22, 2026
- License
- AGPL-3.0
What is AEM MCP?
AEM allows AI agents to manage Adobe Experience Manager instances using natural language for content, components, assets, and workflows.
Summary generated from the project's README
About AEM MCP server
Managing Adobe Experience Manager instances through natural language is the primary function of this MCP server. It is designed for non-technical users who need to interact with content, components, assets, and workflows without writing code. The server supports both AEMaaCS using OAuth S2S authentication with a client ID and client secret, as well as self-hosted instances using standard username and password credentials.
Users can connect via stdio using npx for a zero-install experience or through a streamable HTTP transport for persistent team environments. It integrates with various MCP-compatible clients including AI IDEs like Cursor and VS Code, CLI agents such as Claude Code, and desktop applications like ChatGPT Desktop. The server provides 57 specialized tools and read-only resources that allow agents to discover components, sites, templates, and workflow models automatically.
This tool handles complex tasks like bulk-managing components, performing advanced QueryBuilder searches, and managing content fragment variations. It even supports server-side JSON-string field merging to update specific keys within a JSON-encoded field without requiring a full read-write cycle.
What you can do with it
- 1Manage content fragmentsAn AI agent can perform full CRUD operations and manage variations for both content and experience fragments.
- 2Automate workflow stagesYou can instruct an AI to start, advance, or delegate different stages of an AEM workflow.
- 3Update complex JSON fieldsA developer can ask an AI to merge specific keys into a JSON-encoded string field within a content fragment.
- 4Discover site structuresAn agent can automatically list available templates and site roots to understand the AEM environment.
Written from the project's README. Every use case is checked against a quote from it.
How to install AEM MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall AEM MCP in Claude Code
$ claude mcp add aem-mcp-server -- npx -y aem-mcp-serverInstall AEM MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"aem-mcp-server": {
"command": "npx",
"args": [
"-y",
"aem-mcp-server"
]
}
}
}Install AEM MCP in VS Code
.vscode/mcp.json
{
"servers": {
"aem-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"aem-mcp-server"
]
}
}
}Install AEM MCP in VS Code CLI
$ code --add-mcp '{"name":"aem-mcp-server","type":"stdio","command":"npx","args":["-y","aem-mcp-server"]}'Install AEM MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"aem-mcp-server": {
"command": "npx",
"args": [
"-y",
"aem-mcp-server"
]
}
}
}Install AEM MCP in Codex
$ codex mcp add aem-mcp-server -- npx -y aem-mcp-serverInstall AEM MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.aem-mcp-server] command = "npx" args = ["-y", "aem-mcp-server"]
Install AEM MCP in Gemini CLI
$ gemini mcp add -s user aem-mcp-server npx -- -y aem-mcp-serverInstall AEM MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"aem-mcp-server": {
"command": "npx",
"args": [
"-y",
"aem-mcp-server"
]
}
}
}Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableeasingthemes/aem-mcp-server is public and reachablegithub.com/easingthemes/aem-mcp-server ↗Pass
- Package names this repository as its sourceaem-mcp-server names easingthemes/aem-mcp-server as sourcenpmjs.com/package/aem-mcp-server ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)AGPL-3.0spdx.org/licenses/AGPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-06-22github.com/easingthemes/aem-mcp-server ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from aem-mcp-serverPass
- No critical advisory in the package or its dependencies114 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubAEM MCP Server (aem-mcp-server)
AEM MCP Server is a full-featured Model Context Protocol (MCP) server for Adobe Experience Manager (AEM). It provides a simple integration with any AI Agent. This project is designed for non-technical persons who want to manage AEM via natural language.
Overview
- Manage your AEM instance with natural language — content, components, assets, workflows
- Works with any MCP-compatible client:
- AI IDEs — Cursor, VS Code + Copilot, Windsurf, Cline, JetBrains AI Assistant, Zed
- CLI agents — Claude Code, GitHub Copilot CLI, Gemini CLI, Amazon Q CLI
- Chat & desktop apps — Claude Desktop, ChatGPT Desktop, Goose
- Supports both AEMaaCS and self-hosted AEM instances
- Two transport modes — stdio via
npx(recommended, zero install) and streamable HTTP
Quick Start
Prerequisites
- Node.js 20.19.0+ || 22.12.0+ || 23+
- Access to an AEM instance (local or remote)
Stdio Transport (recommended)
No installation needed — the AI agent downloads and spawns the process automatically via npx.
Add to your project's MCP config (.mcp.json, .vscode/mcp.json, .cursor/mcp.json, etc.):
{
"mcpServers": {
"AEM": {
"command": "npx",
"args": ["-y", "aem-mcp-server", "-t", "stdio", "-H", "http://localhost:4502", "-u", "admin", "-p", "admin"]
}
}
}
Secrets: Since MCP config files are typically committed to the repo, avoid hardcoding credentials. Use your client's env var syntax instead:
Client Syntax Claude Code ( .mcp.json)${AEM_PASSWORD}or${AEM_PASSWORD:-admin}VS Code / Copilot ${input:aem-password}(prompts securely) orenvFileCursor ${env:AEM_PASSWORD}Example with env var references (Claude Code):
{ "mcpServers": { "AEM": { "command": "npx", "args": ["-y", "aem-mcp-server", "-t", "stdio", "-H", "${AEM_HOST:-http://localhost:4502}", "-u", "${AEM_USER:-admin}", "-p", "${AEM_PASSWORD:-admin}"] } } }
Streamable HTTP Transport (alternative)
For scenarios where you need a persistent server (shared team server, multiple clients connecting simultaneously, etc.), install globally and start the server manually:
npm install aem-mcp-server -g
aem-mcp -H=http://localhost:4502 -u=admin -p=admin
Then point your AI agent to the URL:
{
"mcpServers": {
"AEM": {
"url": "http://127.0.0.1:8502/mcp"
}
}
}
Configuration
Options:
--version Show version number [boolean]
-H, --host [string] [default: "http://localhost:4502"]
-u, --user [string] [default: "admin"]
-p, --pass [string] [default: "admin"]
-i, --id clientId [string] [default: ""]
-s, --secret clientSecret [string] [default: ""]
-m, --mcpPort [number] [default: 8502]
-t, --transport Transport mode: http (default) or stdio
[string] [choices: "http", "stdio"] [default: "http"]
-I, --instances Named AEM instances: "local:http://localhost:4502:admin:admin
,qa:https://qa.example.com:user:pass" [string] [default: ""]
-h, --help Show help [boolean]
Authentication:
- For AEMaaCS, use
clientIdandclientSecretfor OAuth S2S authentication. More info. - For self-hosted AEM, use
user/pass. Default credentials areadmin:admin.
Multi-instance: Connect to multiple AEM instances simultaneously:
aem-mcp --instances "author:http://localhost:4502:admin:admin,publish:http://localhost:4503:admin:admin"
All tools will get an instance parameter to target a specific instance.
Features
- 57 MCP Tools covering pages, components, assets, workflows, content fragments, and experience fragments
- MCP Resources — agents discover components, sites, templates, and workflow models upfront via
resources/list, eliminating discovery roundtrips - Tool Annotations — every tool tagged with
group,readOnly, andcomplexityso agents can make smarter tool selection decisions - Response Verbosity —
verbosityparameter (summary/standard/full) on content-reading tools strips JCR internals and truncates long text - Actionable Errors — error responses include
suggestionandalternativesfields for self-healing agent workflows - Component Operations: Update, scan, add, convert, and bulk-manage AEM components (including Experience Fragments)
- Content & Experience Fragments: Full CRUD + variation management for both CF and XF, plus server-side JSON-string field merging (
manageContentFragmentactionmergeJsonField) for CFs that store a whole key→value map inside one JSON-encoded field - Advanced Search: QueryBuilder, fulltext, fuzzy, and enhanced page search
- Replication & Workflows: Publish/unpublish content, start/advance/delegate workflow stages
- Text & Image Extraction: Extract all text and images from pages, including fragments
- Template & Structure Discovery: List templates, analyze page/component structure
- Multi-instance: Connect to multiple AEM instances simultaneously; tools and resources are instance-aware
- Security: Basic auth and OAuth S2S, environment-based config, safe operation defaults
Usage
Once configured in your AI IDE, just ask in natural language:
List all components on MyPage
Merging into a JSON-string field
Some Content Fragments store an entire key→value map inside a single field as a JSON-encoded
string. To upsert a few keys without round-tripping the whole blob, use the mergeJsonField
action — the read-merge-write happens server-side:
{
"action": "mergeJsonField",
"fragmentPath": "/content/dam/<site>/.../labels",
"field": "CFMValue", // the field holding the JSON string
"jsonPointer": "/0/content/0/value", // RFC-6901 pointer to the object to merge into ("" = field root)
"merge": { "search": "Search", "clear_search": "Clear search" },
"variation": "master" // default: master
}
New keys are added, existing keys overwritten (deep-merge), and untouched keys preserved. The response reports the keys added/overwritten and the before/after key count at the pointer.
MCP Resources
The server exposes read-only MCP resources so agents can discover AEM catalogs without tool calls:
| Resource URI | Description |
|---|---|
aem://{instance}/components |
All components (name, resourceType, title, group) |
aem://{instance}/sites |
Site roots and language structure under /content |
aem://{instance}/templates |
Available page templates (path, title) |
aem://{instance}/workflow-models |
Workflow models (ID, title, description) |
Resources return summary data only. In multi-instance mode, each instance gets its own set of resource URIs.
API Documentation
For detailed API documentation, please refer to the API Docs.
Similar Projects
- https://github.com/easingthemes/aem-mcp-server (Used as a base for this project)
- https://github.com/indrasishbanerjee/aem-mcp-server (Used as a base for #1)
- https://www.npmjs.com/package/@myea/aem-mcp-handler (Looks like an original source of #2)
AEM MCP questions
How do I add AEM MCP to Claude Code?
Run claude mcp add aem-mcp-server -- npx -y aem-mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add AEM MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What can I manage with this server?
You can manage content, components, assets, and workflows within your AEM instance using natural language.
Does it support Adobe Experience Manager as a Cloud Service (AEMaaCS)?
Yes, it supports both AEMaaCS and self-hosted AEM instances.