What dependencies does the server require?
The server needs Node.js 16+, MongoDB, and optionally Redis (for scheduled publishing). Medium API credentials and a JWT secret are also required.
@jignesh88
基本信息
Microservice Communication Protocol (MCP) server for Medium's API to publish content and manage user accounts
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Medium MCP API Server is a Model Context Protocol (MCP) server that integrates with Medium’s API to enable seamless content publishing and user account management from external applications. It bridges AI assistants and the Medium publishing platform, handling authentication, draft management, scheduling, and media uploads.
Install it via Docker Compose or manually. Create a .env file with your Medium API credentials, JWT secret, and MongoDB URI. Start the server, then use the provided REST endpoints to register, log in, connect a Medium account, create drafts, publish posts, upload images, and schedule publications. For example, send a POST /api/posts with a title and markdown content, then publish with POST /api/posts/:postId/publish.
The server needs Node.js 16+, MongoDB, and optionally Redis (for scheduled publishing). Medium API credentials and a JWT secret are also required.
Users register or log in via email, receiving a JWT token. A separate OAuth flow connects the user’s Medium account using a client ID and secret.
Published content is sent to Medium and stored there. Drafts, user profiles, and unpublished data are stored in your own MongoDB database.
The server implements rate limiting. All communication is over HTTP using JWT tokens in the Authorization header.
Yes, include a `scheduledAt` ISO timestamp when creating or updating a post. The server will automatically publish at that time if Redis is configured.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Model Context Protocol (MCP) server for TranscriptFetch: fetch YouTube transcripts, search, channels, and playlists from any MCP client.
Find quantum-vulnerable cryptography in your codebase — secp256k1, Ed25519, BLS, Schnorr, RSA. Local, offline MCP server for AI agents.

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.
评论