Skip to main content
Glama
blog-mcp

blog-mcp

by raholsn

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@latest

Open 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

list_articles

Optional tag, limit, offset

Newest posts first, optionally filtered by an exact case-insensitive tag

search_articles

query, optional limit, offset

Keyword matches, with title and tag matches ranked higher

get_article

slug

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-run

Tests 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.js

Only 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 tools
get_articleA
Read-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_articlesA
Read-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_articlesA
Read-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

    A4.7/5.0

    Scored across 3 tools

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness5/5

    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

    ActivityStale
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers