contentful

This MCP server provides a bridge between AI assistants and Contentful APIs, enabling natural language driven content management workflows. It exposes a suite of tools for content types, entries, assets, and space/environment operations that can be invoked by your preferred MCP-enabled AI tool (Codex, Cursor, Claude Desktop, VS Code, etc.). After starting the server with the required Contentful credentials, you can ask the AI to list content types, create or update entries, upload assets, publish or unpublish items, and even automate workflows like translating content or applying bulk updates across entries. The included tool catalog covers initialization, content modeling, and standard CRUD operations, giving your AI assistant end-to-end capabilities to manage a Contentful space directly from natural language prompts.

To use it, configure the MCP server in your AI tool’s MCP settings, providing the required environment variables (CMA token, space ID, environment, and host). Once connected, invoke tools such as list_content_types, create_entry, update_asset, publish_entry, or search_entries as part of your conversations with the AI. The server will translate those tool calls into Contentful Management API requests and return results or error messages to the assistant for ongoing dialogue with the user.

Prerequisites

• Node.js and npm installed on your machine
• Access to a Contentful account with a Space ID and a Content Management API personal access token
• A target Contentful space and environment (default environment_id = master)

Install from source (recommended for development)

1. Clone the repository and install dependencies

git clone https://github.com/contentful/contentful-mcp-server.git
cd contentful-mcp-server
npm install

2. Build (if the project uses a build step)

npm run build

3. Start the MCP server with required environment variables

CONTENTFUL_MANAGEMENT_ACCESS_TOKEN=your-CMA-token \
SPACE_ID=your-space-id \
ENVIRONMENT_ID=master \
CONTENTFUL_HOST=api.contentful.com \
NODE_ENV=production \
npm start

One-click installation (example using Codex integration)

codex mcp add contentful --env CONTENTFUL_MANAGEMENT_ACCESS_TOKEN="your-CMA-token" --env SPACE_ID="your-space-id" --env ENVIRONMENT_ID="master" --env CONTENTFUL_HOST="api.contentful.com" -- npx -y @contentful/mcp-server

Prerequisites recap

• Node.js and npm
• Contentful CMA token and Space ID
• Optional: a specific environment and host overrides

Tips and common issues:

• Ensure the CMA token has the correct permissions for the Space ID and Environment you target.
• If CONTENTFUL_HOST is customized (e.g., for self-hosted Contentful instances), set it accordingly; otherwise the default api.contentful.com works.
• NODE_ENV is optional but can help with debugging; use development during testing and production in production environments.
• The example configuration uses the server name contentful-mcp; you can rename it to fit your MCP workspace, but keep the package/module reference in sync.
• If using Cloud or CI/CD, securely inject environment variables and avoid hardcoding secrets in code or config files.
• When using MCP with multiple AI tools, ensure the host tool supports MCP server connections and that the necessary IPC or webhooks are enabled if required by your setup.