FreshRSS MCP Server
Enables interaction with FreshRSS RSS feed readers through the Google Reader compatible API. Supports feed management, article reading/searching, and marking articles as read or starred.
README
FreshRSS MCP Server
A Model Context Protocol (MCP) server for interacting with FreshRSS via its Google Reader compatible API. This server provides tools for browsing feeds, reading articles, and managing subscriptions. Authentication is handled during server startup.
Features
User Information
get_user_info()- Get authenticated user information
Feed Management
list_subscriptions()- List all RSS feed subscriptionsadd_subscription()- Add new RSS feed subscriptionlist_categories()- List all categories/tags with unread counts
Article Reading
get_articles()- Get articles from feeds, categories, or reading listsearch_articles()- Search articles by keywordsget_starred_articles()- Get all starred articlesget_unread_counts()- Get unread article counts by feed/category
Article Management
mark_article_read()- Mark specific article as readmark_article_starred()- Star/unstar articlesmark_all_as_read()- Mark all articles in a stream as read
Installation
- Install dependencies:
pip install -r requirements.txt
- Run the MCP server with your FreshRSS credentials:
# Using command line arguments
python freshrss_mcp_server.py --url https://your-freshrss-server.com --email your-email@example.com --password your-password
# Or using environment variables
export FRESHRSS_EMAIL="your-email@example.com"
export FRESHRSS_PASSWORD="your-password"
python freshrss_mcp_server.py --url https://your-freshrss-server.com
Usage
Once the server is running and authenticated, you can use the available tools:
Basic Operations
# List subscriptions
subscriptions = await list_subscriptions()
# Get recent articles
articles = await get_articles(count=10)
# Search for articles
results = await search_articles("python", count=5)
# Mark article as read
await mark_article_read("article-id-here")
# Get unread counts
unread = await get_unread_counts()
Stream IDs
Common stream IDs for getting articles:
user/-/state/com.google/reading-list- All articlesuser/-/state/com.google/starred- Starred articlesuser/-/state/com.google/read- Read articlesfeed/[feed-url]- Specific feeduser/-/label/[category]- Specific category
Command Line Options
--url(required): FreshRSS server URL--email: Email address for authentication (can also use FRESHRSS_EMAIL env var)--password: Password for authentication (can also use FRESHRSS_PASSWORD env var)
API Compatibility
This server implements the Google Reader API endpoints that FreshRSS supports:
- Authentication (
/accounts/ClientLogin) - handled at startup - User info (
/reader/api/0/user-info) - Subscriptions (
/reader/api/0/subscription/list,/reader/api/0/subscription/quickadd) - Articles (
/reader/api/0/stream/contents/) - Tagging (
/reader/api/0/edit-tag) - Unread counts (
/reader/api/0/unread-count) - Categories (
/reader/api/0/tag/list)
Requirements
- Python 3.7+
- FastMCP library
- aiohttp for async HTTP requests
- FreshRSS server with API access enabled
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.