Third day, third MCP experiment (inspired by a quick conversation with Dave).
This time I connected Claude with this WordPress blog.
At the end of the chat that I used for the whole process of writing, building and installing the tool on my Mac, I asked Claude to write a post about the experience.
Of course I wouldn’t allow Claude to post unsupervised original stuff to my blog like I just did, but as Dave was pointing out, these are our new writing tools, being able to post directly without having to copy and paste just makes sense.
To be honest I would rather do this with ChatGPT, but apparently MCP integration is not available yet in the UK yet.
Check below to see Claude’s original post.
PS: it also categorised and tagged the post automagically ❤️
The Challenge
As someone who’s been blogging since 2002, I’ve always looked for ways to streamline my writing workflow. With the rise of AI assistants like Claude, I wanted to explore how I could automate blog post creation while maintaining quality and proper formatting.
The Solution: A Custom MCP Server
Today I built a custom Model Context Protocol (MCP) server that connects Claude directly to my WordPress blog. This server handles all the technical complexity of the WordPress REST API whilst providing Claude with simple, powerful tools for content management.
What It Does
The WordPress MCP server provides Claude with three main capabilities:
- Create posts with properly formatted HTML content
- Manage categories and tags automatically (creating new ones when needed)
- Retrieve blog information including existing categories, tags, and recent posts
- Update existing posts and change their publication status
The server intelligently handles WordPress authentication using application passwords and can publish posts immediately or save them as drafts for later review.
Technical Implementation
Built in TypeScript using the MCP SDK, the server:
- Uses WordPress’s REST API with secure authentication
- Automatically creates missing categories and tags
- Supports SEO meta descriptions and custom URL slugs
- Handles both immediate publishing and draft creation
- Provides comprehensive error handling and logging
The Result
I can now ask Claude to research a topic, write a well-structured blog post with proper HTML formatting, categorise it appropriately, and publish it directly to my blog—all in a single conversation. This represents a significant leap forward in AI-assisted content creation whilst maintaining editorial control.
The integration feels seamless and natural, exactly what you’d expect from a mature AI workflow tool.