About Medium MCP API Server
Medium MCP API Server connects external applications to Medium for publishing and account management. It supports drafts, scheduled publication, and image uploads alongside Markdown and HTML content.
Key features
- 01Medium OAuth and profile management
- 02Markdown and HTML publishing
- 03Draft management and scheduling
- 04Tags and publication support
- 05Image uploads and formatting utilities
Use cases
- 01Publish Medium posts from an application
- 02Save drafts and schedule publication
- 03Upload images for article content
- 04Manage Medium user accounts
MCP support
The server bridges MCP clients and the Medium API, exposing content publishing and account management capabilities to AI assistants.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMedium MCP API Server
A Model Context Protocol (MCP) server that integrates with Medium's API to enable seamless content publishing and user account management from external applications. The Model Context Protocol provides a standardized way for AI models to interact with external services and APIs, allowing this server to serve as a bridge between AI assistants and the Medium publishing platform.
🚀 Features
-
Authentication & User Management
- Secure Medium OAuth integration
- JWT-based authentication
- User profile management
-
Content Publishing
- Support for Markdown and HTML content formats
- Draft creation and management
- Post scheduling
- Publication integration
- Tag and category support
-
Media Management
- Image upload and storage
- Content formatting utilities
-
Reliability & Performance
- Redis-based caching
- Job scheduling for post publication
- Comprehensive error handling
- Rate limiting
📋 Requirements
- Node.js 16+
- MongoDB
- Redis (optional, but recommended for scheduling)
- Medium API credentials
🛠️ Installation
Using Docker (Recommended)
-
Clone the repository:
git clone https://github.com/jignesh88/medium-mcp-api.git cd medium-mcp-api -
Create a
.envfile based on the example:cp .env.example .env -
Update the
.envfile with your credentials:MEDIUM_CLIENT_ID=your_medium_client_id MEDIUM_CLIENT_SECRET=your_medium_client_secret MEDIUM_REDIRECT_URI=http://your-domain.com/api/auth/medium/callback JWT_SECRET=your_strong_secret_key -
Start the services using Docker Compose:
docker-compose up -d
Manual Installation
-
Clone the repository:
git clone https://github.com/jignesh88/medium-mcp-api.git cd medium-mcp-api -
Install dependencies:
npm install -
Create and configure your
.envfile -
Start MongoDB and Redis servers
-
Start the application:
npm start
🔐 Medium API Setup
- Create a Medium developer application at https://medium.com/me/applications
- Set the callback URL to
http://your-domain.com/api/auth/medium/callback - Copy your Client ID and Client Secret to your
.envfile
📚 API Documentation
Authentication Endpoints
Register a new user
POST /api/auth/register
Request Body:
{
"email": "[email protected]",
"name": "John Doe"
}
Response:
{
"message": "User registered successfully",
"token": "jwt_token_here",
"user": {
"userId": "user_id",
"email": "[email protected]",
"name": "John Doe"
}
}
Login
POST /api/auth/login
Request Body:
{
"email": "[email protected]"
}
Response:
{
"message": "Login successful",
"token": "jwt_token_here",
"user": {
"userId": "user_id",
"email": "[email protected]",
"name": "John Doe",
"mediumConnected": true
}
}
Connect Medium Account
GET /api/auth/medium
Headers:
Authorization: Bearer jwt_token_here
Response:
{
"authUrl": "https://medium.com/m/oauth/authorize?client_id=..."
}
Content Management Endpoints
Create a Post
POST /api/posts
Headers:
Authorization: Bearer jwt_token_here
Request Body:
{
"title": "My New Post",
"content": "# Markdown Content\n\nThis is my post content.",
"contentFormat": "markdown",
"tags": ["programming", "tutorial"],
"publishStatus": "draft",
"publicationId": "optional_publication_id"
}
Response:
{
"_id": "post_id",
"userId": "user_id",
"title": "My New Post",
"content": "# Markdown Content\n\nThis is my post content.",
"contentFormat": "markdown",
"tags": ["programming", "tutorial"],
"publishStatus": "draft",
"createdAt": "2025-03-16T07:00:00.000Z",
"updatedAt": "2025-03-16T07:00:00.000Z"
}
Publish a Post to Medium
POST /api/posts/:postId/publish
Headers:
Authorization: Bearer jwt_token_here
Response:
{
"message": "Post published successfully",
"post": {
"_id": "post_id",
"mediumPostId": "medium_post_id",
"title": "My New Post",
"published": true,
...
}
}
Get User's Posts
GET /api/posts?status=draft&page=1&limit=10
Headers:
Authorization: Bearer jwt_token_here
Response:
{
"posts": [
{
"_id": "post_id",
"title": "My New Post",
...
}
],
"total": 15,
"page": 1,
"pages": 2
}
Media Management
Upload an Image
POST /api/media/upload
Headers:
Authorization: Bearer jwt_token_here
Content-Type: multipart/form-data
Form Data:
image: [file]
Response:
{
"message": "File uploaded successfully",
"filePath": "/uploads/filename.jpg",
"fileName": "filename.jpg",
"originalName": "my-image.jpg",
"mimeType": "image/jpeg",
"size": 12345
}
🔄 Integrating with the MCP Server
Example: Publishing a post with Node.js
const axios = require('axios');
const API_URL = 'http://your-domain.com';
const TOKEN = 'your_jwt_token';
async function publishPost() {
try {
// Create a draft post
const post = await axios.post(`${API_URL}/api/posts`, {
title: 'My Awesome Article',
content: '# Hello Medium\n\nThis is my first post published via the MCP API.',
contentFormat: 'markdown',
tags: ['api', 'medium', 'tutorial'],
publishStatus: 'draft'
}, {
headers: {
'Authorization': `Bearer ${TOKEN}`
}
});
// Publish the post to Medium
const published = await axios.post(`${API_URL}/api/posts/${post.data._id}/publish`, {}, {
headers: {
'Authorization': `Bearer ${TOKEN}`
}
});
console.log('Post published successfully!', published.data);
} catch (error) {
console.error('Error publishing post:', error.response?.data || error.message);
}
}
publishPost();
📅 Scheduled Publishing
The server supports scheduling posts for future publication. When creating or updating a post, include a scheduledAt field with an ISO timestamp:
{
"title": "Scheduled Post",
"content": "This will be published automatically.",
"scheduledAt": "2025-03-20T12:00:00.000Z"
}
The server will automatically publish the post at the specified time if Redis is configured.
🛡️ Security Considerations
- Always use HTTPS in production
- Rotate your JWT secret regularly
- Set up proper monitoring and logging
- Store sensitive data in environment variables or a secure vault
- Implement proper CORS policies
🔧 Configuration
All configuration is done through environment variables:
| Variable | Description | Required |
|---|---|---|
| PORT | Server port (default: 3000) | No |
| MONGODB_URI | MongoDB connection string | Yes |
| REDIS_URL | Redis connection string | No |
| JWT_SECRET | Secret for JWT tokens | Yes |
| MEDIUM_CLIENT_ID | Medium API client ID | Yes |
| MEDIUM_CLIENT_SECRET | Medium API client secret | Yes |
| MEDIUM_REDIRECT_URI | OAuth callback URL | Yes |
| FRONTEND_URL | URL for frontend redirects | Yes |
📜 License
MIT
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add some amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.