strapi-mcp
Connects any MCP-compatible AI assistant to Strapi CMS for content management, media handling, internationalization, and more through natural language.
README
Strapi MCP Server
AI-powered content management for Strapi CMS via Model Context Protocol.
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
-
Install the server:
pip install strapi-mcp -
Configure your Strapi connection:
export STRAPI_BASE_URL="http://localhost:1337" export STRAPI_API_TOKEN="your-strapi-api-token" -
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
- Open your Strapi Admin panel (e.g.,
http://localhost:1337/admin) - Navigate to Settings > API Tokens
- Click Create new API Token
- Set Token type to Full Access (or customize permissions)
- 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:
- Fetching a content type entry and inspecting its response format
- Checking the admin information endpoint for a version string
- 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
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。