Labsco
darekrossman logo

Contentstack

โ˜… 2

from darekrossman

Interact with Contentstack's Content Management API to manage your CMS content.

๐Ÿ”ฅ๐Ÿ”ฅ๐Ÿ”ฅโœ“ VerifiedAccount requiredAdvanced setup

Contentstack MCP Server

smithery badge

This Model Context Protocol (MCP) server integrates with Contentstack's Content Management API, enabling AI assistants like Claude to interact with your Contentstack CMS through a standardized protocol.

Note: This is an early version of Contentstack MCP Server. See the Roadmap for upcoming improvements and planned features.

contentstack-mcp MCP server

Table of Contents

Features

Available Resources

  • content-types: List all content types (URI: contentstack://content-types)
  • content-type: Get content type by UID (URI: contentstack://content-type/{uid})
  • entries: Get entries by content type (URI: contentstack://entries/{content_type_uid})
  • entry: Get specific entry (URI: contentstack://entry/{content_type_uid}/{entry_uid})
  • assets: List all assets (URI: contentstack://assets)

Content Type Management

  • Create, update, and delete content types
  • Define schemas, options, field rules, and taxonomies
  • Manage global fields

Entry Management

  • Create, update, and delete entries
  • Publish and unpublish entries across environments
  • Query entries with filtering, pagination, and sorting options

Global Field Management

  • Create and update global fields for reuse across content types
  • Retrieve global fields with pagination options

Content Workflows

  • Guided content creation workflows
  • Content analysis and insights
  • Migration planning assistance

Development

Setup for Development

For development, you can use:

npm run dev

This starts the server using ts-node for a faster development cycle.

Code Quality

This project uses Biome.js for linting and formatting. It provides a consistent code style and helps catch potential issues early.

Available Commands

  • Lint Code:

    npm run lint
  • Lint and Fix:

    npm run lint:fix
  • Format Code:

    npm run format
  • Format and Fix:

    npm run format:fix

Integration with AI Assistants

Claude for Desktop

To use this server with Claude for Desktop:

  1. Edit your Claude for Desktop configuration file:

    • Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Add this server to the mcpServers section:

    {
      "mcpServers": {
        "contentstack": {
          "command": "npx",
          "args": ["-y", "@drossman/contentstack-mcp"],
          "env": {
            "CONTENTSTACK_API_KEY": "your_api_key_here",
            "CONTENTSTACK_MANAGEMENT_TOKEN": "your_management_token_here"
          }
        }
      }
    }
  3. Restart Claude for Desktop

Cursor

To use this server with Cursor, add the Contentstack MCP server configuration:

{
   "mcpServers": {
      "contentstack": {
      "command": "npx",
      "args": ["-y", "@drossman/contentstack-mcp"],
      "env": {
         "CONTENTSTACK_API_KEY": "your_api_key_here",
         "CONTENTSTACK_MANAGEMENT_TOKEN": "your_management_token_here",
      }
      }
   }
}

Install with Smithery

You can also install this MCP server using the Smithery CLI using your client of choice:

npx -y @smithery/cli install @drossman/contentstack-mcp --client claude

Available clients include:

  • claude
  • cline
  • windsurf
  • roocode
  • witsy
  • enconvo
  • cursor
  • vscode
  • vscode-insiders
  • boltai
  • amazon-bedrock
  • amazonq

See the Smithery CLI documentation for more details and advanced usage.

Roadmap

  • Enhanced AI Contextual Understanding: Improve context provisioning for complex queries
  • Advanced Querying & Filtering: Support filtering by multiple criteria and custom fields
  • Workflow & Publishing Automation: Enable AI-driven content workflow actions
  • Asset Management Enhancements: Add direct asset manipulation capabilities
  • Bulk Operations Support: Implement batch operations for entries and assets
  • Improved Error Handling & AI Feedback: Refine error messages for AI consumption
  • User-Specific Context & Permissions: Tailor actions based on user permissions
  • Extensibility for Custom Tools: Create an extension framework
  • Real-time Event Handling: Add webhook support for reactive AI behaviors
  • Comprehensive Documentation: Develop detailed guides for AI interaction

Shoutout

Special thanks to Ivo Toby. This project and its author are heavily inspired by his work in this space.