Contentstack

You can connect AI assistants to Contentstack using this MCP server, exposing Contentstack content types, entries, and assets through a standardized interface so your AI workflows can read, create, and manage content within your CMS.

How to use

Install and run the MCP server to enable AI assistants to interact with your Contentstack CMS. You will configure your MCP client to point at the server, then issue requests from your AI tool to list content types, fetch entries, manage assets, and perform basic content workflows. Use the available resources to discover content structures, retrieve specific entries, create or update entries, and publish content across environments.

How to install

# Install globally
npm install -g @drossman/contentstack-mcp

# Or run directly via npx
npx @drossman/contentstack-mcp

Configuration and usage notes

# Environment variables (examples)
CONTENTSTACK_API_KEY=your_api_key_here
CONTENTSTACK_MANAGEMENT_TOKEN=your_management_token_here
# Optional: specify branch if using branches
CONTENTSTACK_BRANCH=your_branch_name

Integration with AI assistants

To connect Claude for Desktop or Cursor to this MCP server, load the MCP configuration into your client and provide the necessary environment variables. The server is accessed by your AI assistant through the MCP client interface, using the npx-based runtime command shown in the examples.

Usage examples

# Example client configuration for Claude/Desktop (JSON snippet shown for reference in your client):
{
  "mcpServers": {
    "contentstack": {
      "command": "npx",
      "args": ["-y", "@drossman/contentstack-mcp"],
      "env": {
        "CONTENTSTACK_API_KEY": "your_api_key_here",
        "CONTENTSTACK_MANAGEMENT_TOKEN": "your_management_token_here"
      }
    }
  }
}

Security and credentials

Keep API credentials secure. Do not embed secrets in your AI prompts. Use environment variables in your MCP client configuration and restrict access to the machine running the MCP server.

Roadmap and notes

This server is an early version with future improvements planned for deeper AI context, enhanced querying, asset handling, and workflow automation. Stay tuned for updates to support more workflows and error handling improvements.

Troubleshooting

If you encounter connection issues, verify that your MCP client is configured with the correct environment variables and that the server process is running. Check for network access, firewall rules, and that the API credentials have the required permissions.

Notes

This MCP server integrates with Contentstack’s API to expose standard resources such as content types, entries, and assets, enabling AI-assisted content creation, updates, and publishing workflows.

Available tools

content-types

List all content types available in the Contentstack space.

content-type

Get a content type by UID.

entries

Fetch entries for a given content type, with support for filtering and pagination.

entry

Get a specific entry by content type UID and entry UID.

assets

List assets in the Contentstack space.

content-workflows

Support guided content creation, analysis, and migration planning.