
MCP Medium Server
Enables AI assistants to publish posts to Medium with support for drafts, tags, canonical URLs, and follower notifications. Supports various publishing statuses and SEO optimization features.
README
MCP Medium Server
A Model Context Protocol (MCP) server that enables AI assistants to publish posts to Medium.
Features
- Publish Posts: Create and publish articles to Medium
- Draft Support: Publish as draft, unlisted, or public
- Tag Management: Add tags to your posts
- Canonical URLs: Set canonical URLs for SEO
- Follower Notifications: Optionally notify followers when publishing
Installation
Via npx (Recommended)
npx mcp-medium
Local Development
git clone <repository-url>
cd mcp-medium
pnpm install
pnpm build
pnpm start
Setup
1. Get Medium API Token
- Go to Medium Settings
- Scroll down to "Integration tokens"
- Generate a new token
- Copy the token for use in your environment
2. Set Environment Variable
export MEDIUM_TOKEN="your_medium_token_here"
3. Configure MCP Client
Add this server to your MCP client configuration:
Claude Desktop (config.json):
{
"mcpServers": {
"medium": {
"command": "npx",
"args": ["mcp-medium"],
"env": {
"MEDIUM_TOKEN": "your_medium_token_here"
}
}
}
}
Other MCP Clients:
npx mcp-medium
Usage
Once configured, you can ask your AI assistant to publish posts to Medium:
"Please publish this article to Medium as a draft with the tags 'programming' and 'typescript'"
"Publish this post to Medium publicly and notify my followers"
Available Parameters
- title (required): The post title
- content (required): The post content (HTML format)
- tags (optional): Array of tags for the post
- canonicalUrl (optional): Canonical URL for SEO
- publishStatus (optional): "draft", "unlisted", or "public" (default: "draft")
Example
// The AI assistant can call this tool:
publishPost({
title: "My First MCP Post",
content: "<h1>Hello World</h1><p>This is my first post via MCP!</p>",
tags: ["mcp", "automation"],
publishStatus: "draft"
})
Development
Build
pnpm build
Development Mode
pnpm dev
Lint
pnpm lint
pnpm fix
Requirements
- Node.js 18+
- Medium account with API access
- Valid Medium integration token
License
MIT
Author
Jay Simons
- Website: https://yaa.bz
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Support
If you encounter any issues or have questions, please file an issue on the repository.
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。