Hatena Blog

You can search Hatena Blog content from Claude by connecting to this MCP server. It exposes functions to search articles by keyword, fetch recent posts, and retrieve article details by URL, enabling seamless integration between Claude and Hatena Blog.

How to use

Use the MCP client to call the available tools and retrieve Hatena Blog data. You can search for articles with a keyword, fetch the latest posts, or get the full article content by URL. When you issue a tool call, you provide the tool name and its required parameters, and you will receive structured results that you can display or summarize in your chat flow.

How to install

Prerequisites: ensure you have Node.js 18.x installed on your machine.

Install dependencies and start the local development server.

npm install
npm run dev

Additional sections

Configuration and usage details are provided below to help you run and integrate the Hatena Blog MCP server with your environment.

Environment variables you may use locally include BLOG_ID to identify your Hatena Blog, CACHE_DURATION to set the in-memory cache lifetime, and FETCH_BASE_URL for the server fetch API base when used as a remote endpoint.

MCP server connections can be used in two ways: a remote HTTP endpoint or a local stdio-based process. The following configurations show both methods explicitly.

Available tools

search_blog

Search Hatena Blog articles by a keyword and return matching posts with limited results.

get_recent_posts

Fetch the most recent Hatena Blog posts up to a specified limit.

get_post_by_url

Retrieve the full details of a Hatena Blog post by its URL.