Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…

Listen to today's AI briefing

Daily podcast — 5 min, AI-narrated summary of top stories

Developer using Claude AI to publish a blog post from Notion to Dev.to, Hashnode, and Medium via an open-source MCP…
Open SourceScore: 74

BlogCast MCP: Publish to Dev.to, Hashnode, and Medium with One Claude Code Command

An open-source MCP server that turns Notion into a publishing hub, letting you deploy blog posts to multiple platforms with a single sentence to Claude.

·Mar 28, 2026·3 min read··125 views·AI-Generated·Report error
Share:
Source: dev.tovia devto_mcp, hn_claude_codeCorroborated

What It Does — A Complete Publishing Agent

BlogCast MCP is an open-source Model Context Protocol (MCP) server that automates the tedious multi-platform publishing workflow. It connects Claude to your Notion workspace, where you write your posts, and then handles the entire deployment process to Dev.to, Hashnode, and Medium.

The core value is automation of the grunt work:

  • Image URL Handling: It automatically downloads images from Notion's expiring CDN links, caches them locally, and re-uploads them to each platform's own CDN.
  • Platform-Specific Formatting: Converts your content to optimized Markdown for Dev.to/Hashnode and clean HTML for Medium.
  • Analytics Sync: Pulls view counts, reactions, and comments from the platforms back into a linked Notion database.
  • Scheduling & AI Checks: You can schedule posts via natural language ("schedule this for Friday 9am") and run pre-publish AI checks for missing excerpts or vague titles.

The entire system runs locally. Your API keys are stored encrypted on your machine, and no data is sent to a third-party server.

Setup — How to Install and Configure with Claude Code

Getting started requires cloning the repo and running a setup script. The project is a monorepo with three packages: the MCP server, an Express backend, and a React dashboard.

  1. Clone and install:
    git clone https://github.com/TheCodeDaniel/blogcast_mcp.git
    cd blogcast_mcp
    npm run setup  # Installs dependencies for all packages
    
  2. Configure Environment: Copy the .env.example to .env and fill in your API keys for Notion, Dev.to, Hashnode, and Medium.
  3. Run the Services: Start the backend and frontend:
    npm run dev:server
    npm run dev:client
    
  4. Integrate with Claude Desktop: The project includes an auto-configuration script. Run npm run configure-claude in the mcp/ directory. This automatically adds the BlogCast MCP server to your Claude Desktop configuration file (claude_desktop_config.json), so you don't have to edit JSON manually.

When To Use It — Your New Publishing Workflow

Once configured, your interaction moves from forms and buttons to conversation with Claude in Claude Code.

  • To publish: "Publish my latest draft on React state management to Dev.to and Hashnode."
  • To manage: "Show me all drafts that are in review." or "What's the view count on my TypeScript post?"
  • To schedule: "Schedule the 'CLAUDE.md best practices' post for tomorrow at 9 AM UTC."

The MCP server exposes tools like list_drafts, preview_post, publish_post, and sync_analytics. Claude Code uses these tools to execute your commands. This transforms Claude from a coding assistant into a full-stack publishing agent, handling the entire workflow from your Notion draft to live post across the web.

This follows a clear trend of MCP servers expanding Claude Code's capabilities beyond pure software development, turning it into a central hub for knowledge work. As noted in our recent coverage of tools like Airut and Weaviate Agent Skills, the ecosystem is rapidly moving towards giving Claude Code direct, secure access to more of your tools and data.

Source: gentic.news · · author= · citation.json

AI-assisted reporting. Generated by gentic.news from multiple verified sources, fact-checked against the Living Graph of 4,300+ entities. Edited by Ala SMITH.

Following this story?

Get a weekly digest with AI predictions, trends, and analysis — free.

AI Analysis

Claude Code users who write technical content should install BlogCast MCP immediately. It eliminates the single biggest time-sink after writing: manual, repetitive publishing. Your workflow should now be: write in Notion (or the included editor), then delegate the entire cross-posting and image-handling process to Claude with a one-line command. This is a prime example of using MCP to give Claude Code **new domains of agency**. Instead of just editing code, it's now managing your content distribution. Configure it once, and you'll save hours per month. This aligns with the strategy we discussed in "Stop Overthinking Your CLAUDE.md"—configure your tools to handle entire workflows, not just single tasks. Furthermore, the auto-configuration script for Claude Desktop is a best practice more MCP server developers should adopt. Manually editing the `claude_desktop_config.json` file is a friction point; tools that handle this for users significantly lower the barrier to entry and increase adoption.
This story is part of
Anthropic's MCP Gambit: Building a Developer Ecosystem While Rivals Stumble
Claude Code's security-first approach and Model Context Protocol create a convergence point as GitHub, OpenAI, and standalone coding tools show vulnerability.
Compare side-by-side
Claude Code vs Claude Agent
Enjoyed this article?
Share:

AI Toolslive

Five one-click lenses on this article. Cached for 24h.

Pick a tool above to generate an instant lens on this article.

Related Articles

From the lab

The framework underneath this story

Every article on this site sits on top of one engine and one framework — both built by the lab.

More in Open Source

View all
Google logo and Gemma 4 branding on a dark gradient background, representing the new open-weight AI model family…
Open SourceBreakthrough
100

Google Releases Gemma 4 Family Under Apache 2.0, Featuring 2B to 31B Models with MoE and Multimodal Capabilities

Google has released the Gemma 4 family of open-weight models, derived from Gemini 3 technology. The four models, ranging from 2B to 31B parameters and including a Mixture-of-Experts variant, are available under a permissive Apache 2.0 license and feature multimodal processing.

engadget.com/Apr 2, 2026/3 min read/Widely Reported
product launchopen sourcegoogle
A sleek interface shows a waveform graph with a transcription panel, highlighting Cohere's ASR model achieving top…
Open Source
95

Cohere Transcribe: 2B-Parameter Open-Source ASR Model Achieves 5.42% WER, Topping Hugging Face Leaderboard

Cohere released Transcribe, a 2B-parameter open-source speech recognition model. It claims a 5.42% average word error rate, beating OpenAI Whisper v3 and topping the Hugging Face Open ASR Leaderboard.

the-decoder.com/Mar 27, 2026/3 min read/Widely Reported
open-sourcespeech-aibenchmarks
Students and instructors collaborate around a workstation in a modern classroom at ENS Paris-Saclay, with code and…
Open Source
65

ENS Paris-Saclay Publishes Full-Stack LLM Course: 7 Sessions Cover torchtitan, TorchFT, vLLM, and Agentic AI

Edouard Oyallon released a comprehensive open-access graduate course on training and deploying large-scale models. It bridges theory and production engineering using Meta's torchtitan and torchft, GitHub-hosted labs, and covers the full stack from distributed training to agentic AI.

admin/Mar 27, 2026/3 min read
open sourcellmsai engineering