Strapi MCP Server
A Strapi v5 backend that exposes MCP endpoints for Google Search Console and Meta Ads, enabling AI agents to automate SEO and marketing workflows.
README
🚀 Strapi MCP Server
A production-ready Strapi v5 application that acts as a Model Context Protocol (MCP) server for marketing and SEO integrations. This project provides extensible, AI-compatible endpoints for integrating services like Google Search Console and Meta Ads into automated workflows.
📌 Overview
This server enables AI agents and external tools to interact with marketing platforms through standardized MCP endpoints. It is designed for scalability, modularity, and real-world automation use cases.
Key Capabilities
- 🔌 MCP-compliant API endpoints (
/api/mcp/*) - 🧠 AI-agent ready tool registry
- 🔐 Authentication & session management
- ⚡ Rate limiting & streaming support
- 🧩 Plugin-based architecture
- 🗂️ Built-in CMS (Articles, Authors, Categories, etc.)
🧩 Core Plugins
1. GSC MCP (Google Search Console)
Provides tools for SEO automation:
- Site management
- Sitemap submission & deletion
- URL inspection
- Indexing status checks
- Health monitoring
2. Meta MCP (Meta Ads: Facebook & Instagram)
Supports marketing automation workflows:
- Campaign insights
- Ads data integration
- Performance tracking
🛠️ Tech Stack
- Strapi v5.42.0
- Node.js (v20 – v24)
- @modelcontextprotocol/sdk v1.29.0
- better-sqlite3 (default database)
- Winston (logging)
- Zod (validation)
⚙️ Getting Started
Prerequisites
- Node.js >= 20 <= 24
- Yarn or NPM
Installation
git clone <your-repo-url>
cd strapi-mcp-server
yarn install
Development
yarn develop
- Admin Panel: http://localhost:1337/admin
- MCP Endpoints: http://localhost:1337/api/mcp/*
Production
yarn build
yarn start
🌱 Seeding Data
Populate the CMS with sample content:
yarn seed:example
📁 Project Structure
src/
├── plugins/
│ ├── gsc-mcp/
│ │ ├── controllers/
│ │ ├── services/
│ │ ├── routes/
│ │ └── utils/
│ └── meta-mcp/
│ ├── controllers/
│ ├── services/
│ └── utils/
│
├── api/
│ ├── article/
│ ├── author/
│ └── category/
│
config/
├── plugins.ts
🔐 Configuration
Both MCP plugins are enabled via:
config/plugins.ts
Environment Variables
You must configure credentials for external services:
- Google Search Console API credentials
- Meta Ads API credentials
Example:
GSC_CLIENT_ID=your_key
GSC_CLIENT_SECRET=your_secret
META_ACCESS_TOKEN=your_token
🤖 MCP Integration
This server exposes MCP-compatible endpoints that allow AI agents to:
- Discover available tools
- Execute SEO and marketing actions
- Automate workflows programmatically
Example Use Cases
- Automated sitemap submission
- SEO health monitoring bots
- Ads performance reporting
- AI-driven marketing automation
Refer to the MCP SDK documentation for client integration details.
📜 Available Scripts
| Command | Description |
|---|---|
yarn develop |
Start development server |
yarn build |
Build admin panel |
yarn start |
Start production server |
yarn seed:example |
Seed sample CMS data |
🧪 Development Workflow
- Fork the repository
- Install dependencies
- Run the development server
- Add or extend MCP tools inside plugins
- Test endpoints via
/api/mcp/*
📈 Future Improvements
- Additional marketing integrations
- Advanced analytics tools
- Role-based access control for MCP tools
- Multi-tenant support
🤝 Contributing
Contributions are welcome!
- Fork the repo
- Create a feature branch
- Commit your changes
- Open a pull request
📄 License
MIT License
💡 Summary
This project bridges AI systems with marketing platforms using the MCP standard—making it easy to build intelligent, automated SEO and advertising workflows on top of Strapi.
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。
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。
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。
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。