inoreader-mcp
The inoreader-mcp server provides a comprehensive interface to the Inoreader RSS reader API, enabling article management, feed organization, and reading workflow automation through Claude.
Authentication & Setup
Authenticate via OAuth 2.0 (
setup_auth) and configure with environment variables
Reading & Articles
Fetch articles with filtering by read/unread/starred status, date range, and stream (
get_articles)Get lightweight article ID lists for counting or batch operations (
get_article_ids)Retrieve full article content (
get_article_content) and search articles (search_articles)Get unread counts for all feeds and folders (
get_unread_counts)
Subscription Management
List all RSS subscriptions with folders, URLs, and metadata (
list_subscriptions)Subscribe to new feeds, edit existing ones, or unsubscribe (
manage_subscription)
Organization & Tagging
Mark articles as read/unread/starred, apply/remove custom tags in batch (
manage_tags,batch_manage_tags)Mark all articles in a feed or folder as read (
mark_all_read)List all folders, tags, and labels (
list_folders_and_tags)Identify, categorize, and reassign uncategorized feeds (
categorize_feeds,reassign_feeds)
Feed Analysis
Bayesian (Beta-Binomial) feed health analysis to evaluate engagement rates and identify low-value feeds (
analyze_feeds)
Saved Items
Retrieve starred articles, saved web pages, and Keep-tagged items with deduplication and source tracking (
get_saved_items)
Account & Rate Limits
Get authenticated user info (
get_user_info)Monitor API rate limits at zero API cost (
get_rate_limit_status); all tools include API cost info (Zone 1 reads, Zone 2 writes) to help manage the ~100 requests/day per zone limit
Pre-built Workflows
Guided prompts for common tasks: triaging unread articles, analyzing feed health, organizing uncategorized feeds, summarizing recent content, and reviewing saved web pages
Provides tools for managing an Inoreader account, allowing users to triage articles, analyze feed health, manage subscriptions, and organize feeds with folders and tags.
Enables interaction with RSS feeds, allowing for article retrieval, unread count tracking, and subscription management via the Inoreader platform.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@inoreader-mcpSummarize the 5 most recent unread articles from my Tech folder"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
inoreader-mcp
MCP server for the Inoreader RSS reader API. Lets Claude help you triage articles, analyze feed health, and manage subscriptions.
Setup
1. Create an Inoreader API application
Go to the Inoreader Developer Portal and create a new application.
Set the redirect URI to
http://localhost:3333/callbackNote your Client ID and Client Secret
2. Add to Claude Code
claude mcp add -s user \
-e INOREADER_CLIENT_ID=your-client-id \
-e INOREADER_CLIENT_SECRET=your-client-secret \
inoreader -- npx inoreader-mcpOr for Claude Desktop, add to your config file:
{
"mcpServers": {
"inoreader": {
"command": "npx",
"args": ["inoreader-mcp"],
"env": {
"INOREADER_CLIENT_ID": "your-client-id",
"INOREADER_CLIENT_SECRET": "your-client-secret"
}
}
}
}3. Authenticate
On first use, ask Claude to call the setup_auth tool. It will give you an OAuth URL to open in your browser. After authorizing, copy the code parameter from the redirect URL and pass it back. Tokens are saved to ~/.config/inoreader-mcp/tokens.json and refresh automatically.
Resources
Context that MCP clients can read directly without tool calls. All are cached after first fetch.
Resource | URI | Description | API Cost |
|
| Current API rate limit usage and remaining budget | 0 |
|
| All feeds with id, title, URL, and folder assignments | 1 Z1 |
|
| Folder and tag structure | 1 Z1 |
|
| Unread counts per feed and folder (non-zero, sorted descending) | 1 Z1 |
Tools
API primitives
Thin wrappers around individual Inoreader API endpoints.
Reading
Tool | Description | API Cost |
| Unread counts for all feeds/folders, sorted by count | 1 Z1 |
| Fetch articles with filters (stream, status, date range, pagination). | 1-2 Z1/page |
| Lightweight ID-only fetch for counting/batch ops. Use | 1 Z1 |
| Full HTML content for specific articles by ID | 1 Z1 |
| Keyword search across all feeds. Supports | 1 Z1/page |
Subscriptions
Tool | Description | API Cost |
| All feeds with folders, URLs, metadata | 1 Z1 |
| Subscribe, edit (rename/move), or unsubscribe | 1 Z2 |
Organization
Tool | Description | API Cost |
| Mark read/unread/starred, apply/remove tags (batch support) | 1 Z2 |
| Apply different tags to different article groups in one call — ideal for triage workflows | 1 Z2/op |
| Mark all items in a feed/folder as read | 1 Z2 |
| All folders and tags with unread counts (unread only; use | 1 Z1 |
Account
Tool | Description | API Cost |
| Authenticated user info | 1 Z1 |
| Check remaining API budget (uses cached headers) | 0 |
Composite tools
Higher-level workflows that combine multiple API calls or add client-side logic.
Feed management
Tool | Description | API Cost |
| Feeds with no folder, as compact tuples | 1 Z1 |
| Bulk-assign feeds to folders from a | 1 Z2/feed |
| Move feeds between folders in bulk | 1 Z2/feed |
| Bayesian feed health analysis with category-level priors | 3+ Z1 |
Saved items
Tool | Description | API Cost |
| Union of starred articles + saved web pages + Keep-tagged items in one call. Deduplicates and adds | 3 Z1 |
| List saved pages with | 1 Z1/page |
| Batch-remove saved pages by ID | 1 Z2 |
Starred articles, saved web pages, and Keep-tagged items are disjoint collections in the Inoreader API. get_saved_items fetches all three and deduplicates them. Each item includes a saved_via array (["starred"], ["saved_web_page", "keep"], etc.) showing which collections it belongs to.
The keep tag (via manage_tags add_tag='keep') protects a page from cleanup without starring it. Use get_saved_web_pages(filter='removable') for pages that are neither starred nor kept.
Z1 = Zone 1 (read), Z2 = Zone 2 (write). Inoreader enforces ~100 requests/day per zone.
Prompts
Pre-built workflows that combine resources and tools into guided tasks.
Prompt | Description | Arguments |
| Review unread articles, summarize each, suggest read/star/skip |
|
| Analyze feed engagement, identify unsubscribe candidates |
|
| Find feeds with no folder and suggest assignments | -- |
| Digest recent articles grouped by source with key themes |
|
| Review saved pages, decide which to keep or remove | -- |
Rate Limits
Every tool description includes its API cost so Claude can budget calls. The get_rate_limit_status tool returns current usage without making any API requests. Inoreader's free tier allows ~100 requests per day per zone.
License
MIT
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/justmytwospence/inoreader-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server