RSS Crawler MCP server

Fetches, parses, and stores RSS feeds in a SQLite database, enabling seamless news and article retrieval for language models through filtering, searching, and Firecrawl-powered article access.
Back to servers
Setup instructions
Provider
mshk
Release date
Mar 17, 2025
Language
TypeScript
Stats
12 stars

The MCP-RSS-Crawler is a server that implements the Message Chain Protocol to fetch RSS feeds and share them with Large Language Models. It allows LLMs to access and process the latest content from your configured RSS feeds through a standardized interface.

Installation Requirements

Before installing the MCP-RSS-Crawler, ensure you have:

  • Bun JavaScript runtime
  • Firecrawl API key
  • Claude Desktop or another MCP client

Installation Steps

  1. Clone the repository:

    git clone https://github.com/username/mcp-rss-crawler.git
    cd mcp-rss-crawler
    
  2. Install dependencies:

    bun install
    
  3. Create a configuration file for Claude Desktop based on the example:

    cp claude_desktop_config.json.example claude_desktop_config.json
    
  4. Edit the claude_desktop_config.json file with your specific configuration:

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

Configuration Options

Configure the server using environment variables or a .env file:

  • PORT: Server port (default: 5556)
  • FIRECRAWL_API_KEY: Your Firecrawl API key for article fetching
  • DB_DIR: Database directory (default: ~/.mcp-rss-crawler)

For detailed logging, you can set:

DEBUG=mcp-rss:*

Using the MCP Server

Starting the Server

The server should start automatically when you launch Claude Desktop after configuration.

Interacting with RSS Feeds

The server implements the Message Chain Protocol (MCP) allowing LLMs to access your RSS feeds. It handles:

  • Fetching and caching of RSS feeds in a SQLite database
  • Filtering feeds by category, source, or keywords
  • Full API endpoints for feed management

Example MCP Interaction

When an LLM sends a request through the MCP protocol, it looks like this:

{
  "messages": [
    {
      "role": "user",
      "content": "What are the latest news from my RSS feeds?"
    }
  ]
}

The server responds with:

{
  "messages": [
    {
      "role": "assistant",
      "content": "Here are the latest articles from your RSS feeds:",
      "name": "rss-mcp"
    },
    {
      "role": "tool",
      "content": "[{\"title\":\"Article Title\",\"summary\":\"Article summary...\",\"published\":\"2025-03-16T04:30:00.000Z\",\"origin\":\"Feed Name\",\"link\":\"https://example.com/article\"}]",
      "name": "rss-feeds"
    }
  ]
}

Troubleshooting

If you encounter issues:

  • Check your network settings and firewall configuration for connection problems
  • Review console logs for error messages and diagnostic information
  • Verify your Firecrawl API key is correctly configured
  • Ensure the database directory exists and is writable

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "rss-crawler" '{"command":"bun","args":["run","apps/mcp-server/src/mcp-cli.ts"],"env":{"PORT":"5556","DB_DIR":"~/.mcp-rss-crawler","FIRECRAWL_API_KEY":""}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "rss-crawler": {
            "command": "bun",
            "args": [
                "run",
                "apps/mcp-server/src/mcp-cli.ts"
            ],
            "env": {
                "PORT": "5556",
                "DB_DIR": "~/.mcp-rss-crawler",
                "FIRECRAWL_API_KEY": ""
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "rss-crawler": {
            "command": "bun",
            "args": [
                "run",
                "apps/mcp-server/src/mcp-cli.ts"
            ],
            "env": {
                "PORT": "5556",
                "DB_DIR": "~/.mcp-rss-crawler",
                "FIRECRAWL_API_KEY": ""
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later