Contentful MCP Server
Contentful Content Management API access with full CRUD and bulk operation support.
Data last scanned today · Reviewed today
Overview
This MCP server provides an interface to Contentful's management capabilities directly within your AI tools. It facilitates full CRUD operations for entries and assets, alongside tools for managing spaces, environments, and content types. Designed with large-scale data in mind, the server implements smart pagination that limits list operations to three items per response. This approach prevents context window overflow and guides the AI through multi-page retrievals. Additionally, it includes support for asynchronous bulk operations and threaded comment management.
Our verdict
With a security score of 34/100, this server is classified as high risk. The primary concern is the lack of read-only mode, as the current implementation grants full write access upon installation. Furthermore, the repository is community-maintained rather than official, and the last update occurred over six months ago. Due to these factors, this tool should only be used in non-production environments by users who have thoroughly reviewed the source code.
- Comprehensive CRUD operations for entries and assets.
- Built-in smart pagination prevents LLM context window overflow.
- Includes tools for asynchronous bulk publishing and updates.
- Small dependency footprint with only eight direct modules.
- No read-only mode restricts use cases for sensitive environments.
- Community-maintained project with no official affiliation.
- Development activity has slowed with no commits in 195 days.
Setup
{
"mcpServers": {
"contentful-mcp": {
"args": [
"-y",
"@ivotoby/contentful-management-mcp-server"
],
"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 |
|---|---|---|
| search_entries | Search for entries using query parameters | low |
| create_entry | Create new entries | medium |
| get_entry | Retrieve existing entries | low |
| update_entry | Update entry fields | medium |
| delete_entry | Remove entries | high |
| publish_entry | Publish entries | medium |
| unpublish_entry | Unpublish entries | medium |
| get_comments | Retrieve comments for an entry with filtering by status (active, resolved, all) | low |
| create_comment | Create new comments on entries with support for both plain-text and rich-text formats. Supports threaded conversations by providing a parent comment ID to reply to existing comments | medium |
| get_single_comment | Retrieve a specific comment by its ID for an entry | low |
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| ChatGPT | ||||
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf |
Frequently asked questions
›How does the server manage large datasets while preventing context window overflow?
The server implements smart pagination on list operations, returning a maximum of 3 items per request along with metadata for navigating remaining results.
›Are threaded conversations supported for comments?
Yes, threaded comments are supported by providing a parent comment ID in the create_comment tool, which also helps work around the 512-character limit.
›Can I perform batch actions on multiple content items?
Yes, the server provides bulk operations, including bulk_publish, bulk_unpublish, and bulk_validate, which process multiple entries or assets in a single asynchronous API call.
›Is this the official Contentful MCP server?
No, this is a community-driven implementation; Contentful maintains its own official MCP server.
Badge
Maintain this server? Add the live badge to your README.