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
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。