Blog RSS

You run a lightweight MCP server that exposes tools to interact with a blog’s RSS/Atom feed. It lets you list posts, fetch individual post content, retrieve recent posts, get blog metadata, and search post content on demand, all via a reusable MCP transport.

How to use

To use this server with an MCP client, start the server locally and connect over the supported MCP transport. The server provides these tools: list_blog_posts, get_blog_post, get_recent_posts, get_blog_info, and search_full_text. Use them to enumerate posts, fetch content, get quick blog insights, and run on-demand full-text searches.

How to install

Prerequisites: Python 3.10 or newer, and optionally a virtual environment.

Install dependencies from the requirements file.

Set the RSS feed URL that the server will use.

Run the MCP server locally.

# Create and activate a virtual environment (optional but recommended)
python -m venv .venv
source .venv/bin/activate  # on macOS/Linux
.venv\Scripts\activate    # on Windows

# Install dependencies
pip install -r requirements.txt

# Set required environment variable for the feed URL
export RSS_FEED_URL="https://www.sirishgurung.com/rss.xml"  # or your target blog feed

# Start the MCP server (using the standard Python command shown in the source)
python main_server.py

# Alternative local run with a virtualenv explicitly named
.venv/bin/python main_server.py

Additional configuration and notes

You can also run the server via Docker for containerized execution. For a basic stdio-based run, set RSS_FEED_URL and start the server with the Python command shown above.

# Run with Docker (stdio transport) using environment variables
docker run --rm -i \
	-e RSS_FEED_URL="https://www.sirishgurung.com/rss.xml" \
	-e MCP_TRANSPORT=stdio \
	blog-rss-mcp:latest

Troubleshooting and tips

If the feed fetch requires CA certificates inside a minimal container, install system CA certificates in the image. Logs are emitted to stderr; stdio transport messages go to stdout. If you upgrade or change the MCP library, verify the run signature against your installed FastMCP version.

Available tools

list_blog_posts

Return a list of blog posts with title and slug (URL) and publication date.

get_blog_post

Fetch a single blog post by slug and return its slug, URL, and content extracted from the page (preferring the article tag in HTML).

get_recent_posts

Provide a simple reverse-ordered list of the most recently published posts.

get_blog_info

Return metadata about the blog, such as title and description.

search_full_text

Perform an on-demand full-text search by fetching posts and searching their content.