strapi-mcp

strapi-mcp

Connects any MCP-compatible AI assistant to Strapi CMS for content management, media handling, internationalization, and more through natural language.

Category
访问服务器

README

Strapi MCP Server

AI-powered content management for Strapi CMS via Model Context Protocol.

PyPI version License: MIT Python 3.11+

Features

Connect any MCP-compatible AI assistant (Claude, Cursor, etc.) to your Strapi CMS. Manage content, media, locales, and more through natural language.

20 Tools across 8 categories

Category Tools Description
Schema (3) list_content_types, get_content_type_schema, get_components Discover and inspect content models
Content (5) list_entries, get_entry, create_entry, update_entry, delete_entry Full CRUD for any content type
Media (3) upload_media, list_media, delete_media Upload, browse, and manage media library
Publish (3) publish_entry, unpublish_entry, discard_draft Control publication lifecycle
i18n (2) list_locales, get_localized_entry Internationalization support
Search (2) search_entries, count_entries Full-text search and counting
Bulk (1) bulk_action Batch create, update, or delete
System (1) get_strapi_info Server info and version detection

Additional MCP capabilities

  • 3 Prompts: manage_content, content_migration, setup_guide -- guided workflows for common tasks
  • 1 Resource: strapi://help -- comprehensive usage guide with examples

Quick Start

  1. Install the server:

    pip install strapi-mcp
    
  2. Configure your Strapi connection:

    export STRAPI_BASE_URL="http://localhost:1337"
    export STRAPI_API_TOKEN="your-strapi-api-token"
    
  3. Connect from your MCP client (see Client Configuration below).

Installation

Using pip

pip install strapi-mcp

Using uvx (no install required)

uvx strapi-mcp

From source

git clone https://github.com/alexzimmermann/strapi-mcp.git
cd strapi-mcp
pip install -e .

Configuration

All settings are configured via environment variables with the STRAPI_ prefix:

Variable Default Description
STRAPI_BASE_URL http://localhost:1337 URL of your Strapi instance
STRAPI_API_TOKEN (empty) API token for authentication. Create in Strapi Admin > Settings > API Tokens.
STRAPI_API_VERSION auto Strapi version: auto, v4, or v5
STRAPI_TIMEOUT 30 HTTP request timeout in seconds
STRAPI_MAX_PAGE_SIZE 100 Maximum entries per page (1-100)

You can also place these in a .env file in your working directory.

Creating a Strapi API Token

  1. Open your Strapi Admin panel (e.g., http://localhost:1337/admin)
  2. Navigate to Settings > API Tokens
  3. Click Create new API Token
  4. Set Token type to Full Access (or customize permissions)
  5. Copy the generated token and set it as STRAPI_API_TOKEN

Client Configuration

Claude Desktop

Add to your Claude Desktop config file (claude_desktop_config.json):

{
  "mcpServers": {
    "strapi": {
      "command": "uvx",
      "args": ["strapi-mcp"],
      "env": {
        "STRAPI_BASE_URL": "http://localhost:1337",
        "STRAPI_API_TOKEN": "your-strapi-api-token"
      }
    }
  }
}

Cursor

Add to your Cursor MCP config:

{
  "mcpServers": {
    "strapi": {
      "command": "uvx",
      "args": ["strapi-mcp"],
      "env": {
        "STRAPI_BASE_URL": "http://localhost:1337",
        "STRAPI_API_TOKEN": "your-strapi-api-token"
      }
    }
  }
}

Smithery

This server is available on Smithery. Install directly from the Smithery registry or configure manually using the smithery.yaml included in this repository.

Available Tools

Tool Description
list_content_types List all available content types in the Strapi instance
get_content_type_schema Get the full field schema for a specific content type
get_components List all reusable components and their schemas
list_entries List entries with filtering, sorting, pagination, and population
get_entry Get a single entry by ID (or documentId in v5)
create_entry Create a new content entry with field data
update_entry Update an existing entry by ID
delete_entry Delete an entry by ID
upload_media Upload a file to the media library (URL or base64)
list_media Browse the media library with pagination
delete_media Delete a file from the media library
publish_entry Publish a draft entry to make it publicly available
unpublish_entry Revert a published entry to draft status
discard_draft Discard unsaved draft changes (Strapi v5 only)
list_locales List all configured locales for i18n
get_localized_entry Get an entry in a specific locale
search_entries Full-text search across entries of a content type
count_entries Count entries matching optional filter criteria
bulk_action Perform bulk create, update, or delete operations
get_strapi_info Get Strapi server info, version, and connection status

Strapi Version Support

This server supports both Strapi v4 and Strapi v5 with automatic version detection.

Auto-detection

When STRAPI_API_VERSION is set to auto (the default), the server detects your Strapi version at startup by:

  1. Fetching a content type entry and inspecting its response format
  2. Checking the admin information endpoint for a version string
  3. Defaulting to v5 if detection is inconclusive

Key differences handled automatically

Feature Strapi v4 Strapi v5
Entry format Nested data.attributes Flat with documentId
Entry identifier Numeric id String documentId
Publication status publicationState=live|preview status=published|draft
Draft discard Not available discard_draft tool

You can force a specific version by setting STRAPI_API_VERSION=v4 or STRAPI_API_VERSION=v5.

Development

Setup

git clone https://github.com/alexzimmermann/strapi-mcp.git
cd strapi-mcp
python -m venv .venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows
pip install -e ".[dev]"

Running tests

pytest

Running with coverage

pytest --cov=strapi_mcp --cov-report=term-missing

Code style

ruff check .
ruff format .

License

MIT License. See LICENSE for details.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选