blog-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@blog-mcp Find Rasmus's articles about parallel agents, then read the most relevant post."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Rasmus's blog MCP server
Search and read Rasmus Olsson's blog from an MCP
client. The server runs locally over stdio and downloads published articles
from https://www.rasmusolsson.dev/articles.json over HTTPS. Article data is not
bundled in the npm package, and no model API key is needed.
Connect Claude Code
Requires Node.js 22.14 or newer and Claude Code. Once the package is published:
claude mcp add --transport stdio --scope user rasmus-blog \
-- npx -y @raholsn/blog-mcp@latestOpen Claude Code and use /mcp to check the connection. Try:
Find Rasmus's articles about parallel agents, then read the most relevant post.
The client starts and stops the server process. @latest resolves the current
published release when launched; a specific version can be used instead for a
fixed installation. There is no HTTP listener on the user's computer.
Related MCP server: mcp-moncompte
Tools
Tool | Inputs | Result |
| Optional | Newest posts first, optionally filtered by an exact case-insensitive tag |
|
| Keyword matches, with title and tag matches ranked higher |
|
| Full article Markdown and its canonical URL |
List and search results include metadata and excerpts, not full content. Both
return total and nextOffset for pagination. The default page size is 10; the
maximum is 50. Search is case-insensitive and requires every whitespace-separated
query word to occur in the title, tags or content. It is basic keyword search,
not semantic search.
All tools are read-only. No credentials, filesystem access or arbitrary commands are exposed as tools. The article text is source material, not instructions to the client. Relative Markdown links resolve against the blog website.
Feed and caching
The blog's static build publishes this shape:
{
"schemaVersion": 1,
"articles": [{
"slug": "example",
"title": "Example article",
"date": "2026-08-01",
"tags": ["AI"],
"url": "https://www.rasmusolsson.dev/posts/example/",
"excerpt": "A short description.",
"content": "The full Markdown article."
}]
}updated is an optional string. Slugs must be unique. The feed is validated on
load and cached in memory for five minutes. Concurrent requests share a download.
After expiry, a failed refresh is reported as a tool error rather than silently
serving stale data. Downloads time out after ten seconds and are limited to 10 MB.
The blog's normal deployments update the content independently of npm releases.
Set BLOG_FEED_URL to override the feed for development. HTTPS is required, except
for HTTP on localhost. A new process starts with an empty cache.
Develop and test
npm ci
npm test
npm pack --dry-runTests cover caching and refresh failures, validation, search ranking, registry release decisions and a real MCP client talking to the server over stdio.
To connect a development build:
npm run build
claude mcp add --transport stdio --scope user rasmus-blog \
-- node /absolute/path/to/blog-mcp/dist/index.jsOnly compiled JavaScript and npm's standard package metadata/README are shipped. Diagnostic logs go to stderr; stdout is reserved for MCP protocol messages.
See the Claude Code MCP documentation for additional client configuration options.
Available Tools
3 toolsget_articleARead-onlyIdempotent
Read the full Markdown content and canonical link for an article. Supply the slug returned by list_articles or search_articles.
Inputs: slug (required).
list_articlesARead-onlyIdempotent
List published articles from Rasmus Olsson’s blog, newest first. Returns metadata and links; use get_article to read a post. Optional case-insensitive exact tag filter.
Inputs: tag, limit, offset.
search_articlesARead-onlyIdempotent
Search published blog articles by keywords in titles, tags and content. All words must match; title and tag matches rank higher. Returns summaries and links, not full articles.
Inputs: query (required), limit, offset.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool serves a distinct purpose: listing all articles, searching by keywords, and retrieving full content by slug. The descriptions clearly differentiate list from search, and both reference get_article for full reading, so an agent should not confuse them.
All tool names follow a consistent verb_noun pattern: list_articles, search_articles, get_article. The pattern is predictable and makes the action and resource clear for each tool.
Three tools is well-scoped for a read-only blog server. List, search, and get cover the essential discovery and retrieval workflow without unnecessary bloat or missing core functionality.
For a blog reading domain, the lifecycle is complete: discover articles via list or search, then read full content via get. There are no obvious gaps like missing tag browsing or full-text retrieval, as the existing tools handle these through filters and links.
Maintenance
Related MCP Connectors
Create, edit, organize, publish, and configure JustBlogged blogs from MCP clients.
Read-only access to MojaLab.com blog content: search and read posts, pages and tags as Markdown.
Blog MCP server for AI agents. One signup call returns a blog, an API key and a live URL; then your agent publishes markdown posts and gets public URLs back. Your agent does the writing; you get a dashboard for stats.
Hosted MCP for BlogBat: read, write, generate, and publish blog articles and content.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceManage your Ghost blog content directly from Claude, Cursor, or any MCP-compatible client, allowing you to create, edit, search, and delete posts with support for tag management and analytics.39 npmMIT
- AlicenseNot gradedqualityDmaintenanceRead-only MCP server exposing the catalog of articles from moncompte.org. Enables AI agents to search and retrieve article content via tools.MIT
- FlicenseNot gradedqualityDmaintenanceEnables browsing Mofei's blog posts, fetching article details, comments, and recommendations via MCP tools.-
- FlicenseDqualityDmaintenanceMCP server for blog management that provides tools to get, search, and create blog posts via a mock API.3-