MCP-RSS-Crawler

RSS Crawler MCP Server

typescript

19

GitHub Stars

typescript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mshk-mcp-rss-crawler": {
      "command": "/path/to/bun",
      "args": [
        "run",
        "/path/to/mcp-rss-crawler/apps/mcp-server/src/mcp-cli.ts"
      ],
      "env": {
        "PORT": "5556",
        "DB_DIR": "/path/to/mcp-rss-crawler",
        "FIRECRAWL_API_KEY": "fc-<YOUR_FIRECRAWL_API_KEY>"
      }
    }
  }
}

You run an MCP server that fetches RSS feeds, caches them locally, and exposes the latest articles to LLMs via the Message Chain Protocol. This enables your language models to access up-to-date content from your preferred feeds without leaving their context.

How to use

You connect your MCP client to the RSS crawler to retrieve the latest articles from your RSS feeds. Your client sends a request containing a user message, and the server responds with a structured set of feed items that match the request. The server handles RSS fetching, caching, filtering by category/source/keywords, and can fetch articles from Firecrawl when configured.

How to install

Prerequisites you must have before installing:

Bun runtime
Firecrawl API key
Claude Desktop or another MCP client to connect to the server Follow these concrete steps to set up the server and run it locally.

Create the configuration file for Claude Desktop using the example structure provided below. This file tells Claude Desktop how to locate and run your MCP server.

Prepare the MCP server configuration. Create a file with the following content to describe how to start the server via Bun and your MCP CLI entry point.

Install dependencies with Bun.

bun install

Start Claude Desktop and connect to your MCP server using the configured MCP path.

Available tools

fetch_rss

Fetch RSS feeds from configured sources and cache them in a local SQLite database for fast reuse by the MCP server.

cache_db

Store and retrieve feed data locally to minimize repeated network calls and provide offline access to recently fetched items.

filter_feeds

Filter feeds by category, source, or keywords to tailor results returned to the MCP client.

manage_feeds_api

Comprehensive API endpoints to add, update, and delete feeds and control feed management from MCP clients.

fetch_firecrawl

Optionally fetch articles from Firecrawl when configured and include them in MCP responses.