OfficialVerified

Contentful MCP Server

Manage, create, and organize Contentful entries and assets via AI-driven commands.

Data last scanned 2 days ago · Reviewed 2 months ago

68 6 dangerous tools45 tools★ 58TypeScriptMIT

Overview

This server integrates with Contentful APIs to provide direct content management capabilities for AI assistants. It supports a variety of operations including content creation, updating existing entries, asset organization, and content modeling, allowing for natural language-driven workflows directly within your space.

Our verdict

With a security score of 25/100, this server is considered high-risk. It lacks OAuth support and requires a personal access token for authentication, while simultaneously defaulting to full write access without a read-only mode, meaning any configured user has broad authority over your content. It is recommended only for power users who understand the implications of full API exposure and can secure their environment variables appropriately.

Supports comprehensive Contentful content management and modeling.
Zero direct dependencies minimizes supply-chain surface area.
Active development with 16 contributors.

Lacks OAuth support for granular access control.
No read-only mode provided for safer operations.
Community-maintained rather than official vendor software.
No authentication method beyond basic configuration tokens.

Setup

Claude Desktop

{
  "mcpServers": {
    "contentful-mcp-server": {
      "args": [
        "-y",
        "contentful-mcp-tools"
      ],
      "command": "npx"
    }
  }
}

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows), then restart Claude Desktop. Some servers require API keys or tokens as environment variables — check the project's README and add an "env" object if needed.

No read-only mode — running this grants full read/write access.
No built-in authentication — anyone with access to this config can invoke every tool it exposes.

Tools

Tool	Description	Risk
get_initial_context	Initialize connection and get usage instructions	low
list_content_types	List all content types	low
get_content_type	Get detailed content type information	low
create_content_type	Create new content types	medium
update_content_type	Modify existing content types	medium
publish_content_type	Publish content type changes	medium
unpublish_content_type	Unpublish content types	medium
delete_content_type	Remove content types	high
search_entries	Search and filter entries	low
semantic_search	Find entries by meaning (vector search)	low

Compatibility

Client	Local	Docker	Remote	Read-only
Claude Desktop
Cursor
VS Code
Windsurf
ChatGPT

Frequently asked questions

›What prerequisites are needed to use this server?

You need Node.js, npm, a Contentful account with a Space ID, and a Contentful Management API personal access token.

›How can I prevent accidental writes to production environments?

You can use the PROTECTED_ENVIRONMENTS environment variable, which accepts a comma-separated list of environment IDs to block write and delete operations.

›Are read operations affected when an environment is marked as protected?

No, read operations such as get, list, and search functions remain fully functional even if an environment is listed in PROTECTED_ENVIRONMENTS.

›Is the protection feature an alternative to Contentful's built-in role-based permissions?

No, this feature is an MCP boundary guard that runs within the server itself and should be used alongside, not instead of, native Contentful permissions.

›How do I configure the environment ID the server interacts with?

You can specify the target environment by setting the ENVIRONMENT_ID variable; it defaults to 'master' if left unset.