Article Writer MCP
Enables automated content creation pipeline: topic research, article writing, image sourcing, and GitHub PR submission for blogs.
README
Article Writer MCP
An MCP server that runs a full content pipeline from Claude chat: finds trending topics in your niche, researches them for real facts, writes a full article in your brand voice, sources a licensed image, and can push the finished piece straight to your website's GitHub repo as a pull request.
Built for Wayzyy, a Goa vacation rental marketplace —
but the brand-specific bits are pulled into config.yaml so you can point
this at your own blog/niche.
Setup
pip install -r requirements.txt- Copy
.env.exampleto.envand fill in your API keys (Kimi, Groq, Firecrawl, Pexels) - Edit
config.yamlwith your own brand name, blog URL, and site repo path - Register the server in your Claude Desktop config, pointing at
mcp_server.py
What's genericized vs. what still needs work
config.yaml covers the structural stuff — brand name, blog URL, contact
email, niche, and the closing CTA wording. That's enough to get the pipeline
running for a different site without touching Python code.
Not yet genericized: the deeper brand-voice content in prompts/style_guide.py
and prompts/article_format.py (banned phrases, tone rules, article structure
templates) and the site-specific TSX conversion logic in agent/site_publisher.py
(built against Wayzyy's exact Vite/React blog format — a different site's blog
will need its own version of that converter). Treat those as the files to
rewrite for your own brand/site.
Tools
run_scanner— find trending topics via Google News RSS, deduped against what you've already publishedsuggest_next_article— ranked recommendations with real evidencewrite_article— full pipeline: research → outline → write → image → style check → saveget_draft/preview_draft/open_draft— review the draft (text, rendered localhost page, or a real editor)run_style_check— quality reportedit_draft— request changes, rewritten and saved automaticallysave_draft— save edited text directly, no LLM call neededpush_to_github— converts to your site's format and opens a real PR for review
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.