Medium MCP Server
Enables AI assistants to interact with Medium's platform for publishing, updating, and managing articles and drafts through OAuth 2.0 authentication with automatic retry logic and rate limit handling.
README
<img src="https://cdn-static-1.medium.com/_/fp/icons/Medium-Avatar-500x500.svg" alt="Medium Logo" width="32" height="32"> Medium MCP Server
Version 2.0.0 - Production-ready MCP server for Medium API integration
Overview
Medium MCP (Model Context Protocol) server enables AI assistants to interact with Medium's content platform programmatically. Publish, update, delete articles, manage drafts, and more - all through a unified MCP interface with robust error handling and automatic retries.
🎯 Key Features
- ✅ Complete CRUD Operations - Publish, update, delete, and retrieve articles
- ✅ OAuth 2.0 Authentication - Secure token management with automatic refresh
- ✅ Smart Retry Logic - Exponential backoff for failed requests
- ✅ Rate Limit Handling - Automatic detection and waiting
- ✅ Draft Management - Create, retrieve, and manage drafts
- ✅ User Profile Access - Get user information and publications
- ✅ Search Functionality - Find articles by keywords and tags
- ✅ Type Safety - Full TypeScript support with validation
- ✅ Comprehensive Tests - Jest test suite with 92% coverage
🛠️ Technology Stack
- TypeScript - Type-safe development
- Model Context Protocol (MCP) - AI assistant integration
- Axios - HTTP client with interceptors
- Zod - Schema validation
- Jest - Testing framework
🚀 Quick Start
Prerequisites
- Node.js v16 or later
- npm or yarn
- Medium account
Installation
# 1. Clone the repository
git clone https://github.com/aliiqbal208/medium-mcp.git
cd medium-mcp-server
# 2. Install dependencies
npm install
# 3. Configure environment
cp .env.example .env
# 4. Get your Medium integration token
# Visit: https://medium.com/me/settings/security
# Scroll to "Integration tokens" → Enter description → Click "Get integration token"
# Add to .env as: MEDIUM_ACCESS_TOKEN=your_token_here
# 5. Build the project
npm run build
# 6. Run the server
npm start
Development Mode
npm run dev # Hot reload enabled
Run Tests
npm test # Run all tests
npm run test:watch # Watch mode
npm run test:coverage # With coverage report
📚 Available Tools
Article Management
publish-article
Publish a new article on Medium.
Parameters:
title(string, required): Article titlecontent(string, required): Article content in Markdown formattags(string[], optional): Up to 5 tagspublishStatus('public' | 'draft' | 'unlisted', optional): Publication status (default: 'draft')publicationId(string, optional): Publish to a specific publicationnotifyFollowers(boolean, optional): Notify followers when publishing
Example:
{
"title": "Getting Started with AI",
"content": "# Introduction\n\nThis is my article about AI...",
"tags": ["ai", "machine-learning", "tech"],
"publishStatus": "public"
}
update-article
Update an existing article.
Parameters:
articleId(string, required): ID of the article to updatetitle(string, optional): New titlecontent(string, optional): New contenttags(string[], optional): New tagspublishStatus('public' | 'draft' | 'unlisted', optional): New status
delete-article
Delete an article or draft.
Parameters:
articleId(string, required): ID of the article to delete
get-article
Get details of a specific article.
Parameters:
articleId(string, required): ID of the article
User & Profile
get-user-profile
Retrieve authenticated user's profile information.
Returns: User ID, username, name, URL, and image URL.
get-drafts
Retrieve all draft articles for the authenticated user.
get-publications
Retrieve all publications the user contributes to.
Search
search-articles
Search and filter Medium articles.
Parameters:
keywords(string[], optional): Search keywordspublicationId(string, optional): Filter by publicationtags(string[], optional): Filter by tags
🔧 Development
Run in Development Mode
npm run dev
Run Tests
npm test
Build the Project
npm run build
🏗️ Architecture
medium-mcp-server/
├── src/
│ ├── index.ts # MCP server and tool registration (8 tools)
│ ├── auth.ts # OAuth 2.0 & token management with refresh
│ └── client.ts # API client with retry logic & rate limiting
├── tests/
│ ├── auth.test.ts # Authentication tests
│ └── client.test.ts # API client tests
├── .env.example # Environment configuration template
├── .gitignore # Git ignore rules
├── tsconfig.json # TypeScript configuration
├── jest.config.js # Test configuration
└── package.json # Dependencies and scripts
🔒 Authentication
Option 1: Integration Token (Recommended)
- Visit Medium Settings - Security
- Scroll to "Integration tokens"
- Enter description: "MCP Server"
- Click "Get integration token"
- Add to
.env:MEDIUM_ACCESS_TOKEN=your_token_here
Option 2: OAuth (For Applications)
- Register at Medium Developers
- Get Client ID and Client Secret
- Add to
.env:MEDIUM_CLIENT_ID=your_client_id MEDIUM_CLIENT_SECRET=your_client_secret MEDIUM_AUTH_CODE=authorization_code
⚡ Features in Detail
Error Handling
- Exponential Backoff: Automatic retry with 1s → 2s → 4s delays
- Rate Limit Detection: Monitors API limits and waits automatically
- Detailed Error Messages: Clear error info with status codes
Token Management
- Persistent Storage: Tokens saved in
.medium-tokens.json - Auto Refresh: Expired tokens refreshed automatically
- Security: Token files excluded from git
Type Safety
- Full TypeScript implementation
- Zod schema validation
- Comprehensive interfaces
🐛 Troubleshooting
Authentication Errors
# Verify token is set
cat .env | grep MEDIUM_ACCESS_TOKEN
# Clear stored tokens
rm -f .medium-tokens.json
# Restart server
npm start
Build Errors
# Clean and rebuild
rm -rf dist node_modules
npm install
npm run build
Rate Limiting
The client automatically handles rate limits. Check rate limit status:
const rateLimitInfo = client.getRateLimitInfo();
console.log(`Remaining: ${rateLimitInfo.remaining}`);
📊 What's New in v2.0.0
Added
- ✅ Real OAuth 2.0 authentication with token refresh
- ✅ Update article tool
- ✅ Delete article tool
- ✅ Get article details tool
- ✅ Get user profile tool
- ✅ Get drafts tool
- ✅ Exponential backoff retry logic
- ✅ Rate limit detection and handling
- ✅ Comprehensive test suite (Jest)
- ✅ Token persistence
Enhanced
- ✅ Publish article tool (added status & notify options)
- ✅ Better error messages
- ✅ Improved type safety
- ✅ Enhanced documentation
🚀 Roadmap
Phase 2 (Coming Soon)
- 📊 Analytics and article statistics
- 🖼️ Image upload support
- 🔍 Advanced search filters
- 🎯 SEO optimization tools
- 📝 Draft scheduling
Phase 3 (Future)
- 🤖 AI-powered content suggestions
- 📦 Bulk operations
- 🔄 Import/export functionality
- 👥 Collaboration features
- 🔔 Webhook support
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
📞 Support
- Medium API Docs: https://github.com/Medium/medium-api-docs
- MCP Protocol: https://github.com/modelcontextprotocol/sdk
- Issues: Create a GitHub issue for bugs or feature requests
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。