Crypto RSS MCP
About
An MCP server that aggregates real-time cryptocurrency news from multiple RSS feeds.
Details
- License
- MIT
Explore
- Feed Retrieval: Fetches latest entries from specified RSS feeds, formatting them as Markdown with plain-text summaries.
- Keyword Filtering: Filters feeds by keyword in descriptions or categories.
- OPML Support: Import feed list from a local OPML file provided by Chainfeeds.
- LLM Integration: Includes a prompt for analyzing feed content to summarize key points and identify cryptocurrency market trends.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Crypto RSS MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python: Version 3.10.
- uv: Package and dependency manager for Python projects.
Start the FastMCP server in development mode:
uv run mcp dev cli.py
Install the server as a Claude Desktop application:
uv run mcp install cli.py --name "Crypto RSS Reader"
Configuration file as a reference:
{
"mcpServers": {
"Crypto RSS Reader": {
"command": "uv",
"args": [ "--directory", "/path/to/crypto-rss-mcp", "run", "crypto-rss-mcp" ]
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"crypto rss mcp": {
"crypto-rss-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}
}
}McpServers
{
"crypto-rss-mcp": {
"command": "uv",
"args": [
"sync"
]
}
}An MCP server that aggregates real-time cryptocurrency news from multiple RSS feeds, helping AI agents make informed decisions in a fast-paced market.
<a href="https://glama.ai/mcp/servers/@kukapay/crypto-rss-mcp">
</a>
Features
- Feed Retrieval: Fetches latest entries from specified RSS feeds, formatting them as Markdown with plain-text summaries.
- Keyword Filtering: Filters feeds by keyword in descriptions or categories.
- OPML Support: Import feed list from a local OPML file provided by Chainfeeds.
- LLM Integration: Includes a prompt for analyzing feed content to summarize key points and identify cryptocurrency market trends.
Prerequisites
- Python: Version 3.10.
- uv: Package and dependency manager for Python projects.
Installation
1. Clone the Repository:
git clone https://github.com/kukapay/crypto-rss-mcp.git
cd crypto-rss-mcp
2. Install Dependencies:
Add the required dependencies using uv:
uv sync
Usage
Running the Server
Start the FastMCP server in development mode:
uv run mcp dev cli.py
Installing to Claude Desktop
Install the server as a Claude Desktop application:
uv run mcp install cli.py --name "Crypto RSS Reader"
Configuration file as a reference:
{
"mcpServers": {
"Crypto RSS Reader": {
"command": "uv",
"args": [ "--directory", "/path/to/crypto-rss-mcp", "run", "crypto-rss-mcp" ]
}
}
}
Available Tools
get_crypto_rss_list
Lists available RSS feeds from an OPML file, optionally filtered by keyword.
Parameters:
- keyword (str, optional): Filter feeds where the keyword appears in the description or category (case-insensitive).
- opml_file (str, optional): Path to a local OPML file (defaults to "RAW.opml").
Example:
> List available cryptocurrency RSS feeds
Output:
Available Cryptocurrency RSS Feeds:
Category: 05. Research/VC
URL: https://b10c.me/feed.xml
Description: 0xB10C's Blog: German Bitcoin freelance developer on 0xB10C's Blog
Category: 03. Media
URL: https://bitcoinmagazine.com/feed
Description: Bitcoin Magazine
...
get_rss_feed
Fetches and formats the latest 10 entries from a specified RSS feed as Markdown.
Parameters:
- feed_url (str): The URL of the RSS feed to fetch.
Example:
> Read this RSS feed: https://blog.0xproject.com/feed
Output:
```
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
