Inoreader MCP. Curate and organize hundreds of news sources.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Inoreader lets you connect your entire news consumption stack—hundreds of RSS feeds and blogs—to any AI agent. It fetches article content, manages tags, tracks unread counts across all sources, and keeps your knowledge base organized through natural language commands.
What your AI agents can do
Delete tag
Removes a tag or folder from articles; the article content remains untouched.
Edit tag
Adds, removes, or changes tags on specific articles for better categorization.
Get unread counts
Retrieves the total number of unread items found within a specific feed or folder.
List all current feeds or subscribe to a new source using just a URL.
Fetch specific articles from any designated feed, folder, or tag for processing.
Group, rename, or delete tags and folders to maintain a clean information structure.
Check exactly how many items you haven't read across your entire collection of sources.
Mark all articles in an entire stream as read instantly, or get basic user profile data.
Ask AI about this MCP
Supported MCP Clients
OAuth 2.0 Compatible Gemini Waiting for input…
Inoreader MCP: 10 Tools
Use these tools to manage subscriptions, categorize content, and track reading status across all your connected feeds.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Inoreader on Vinkius019dd10bdelete tag
Removes a tag or folder from articles; the article content remains untouched.
019dd10bedit tag
Adds, removes, or changes tags on specific articles for better categorization.
019dd10bget unread counts
Retrieves the total number of unread items found within a specific feed or folder.
019dd10bget user info
Pulls basic account information associated with your Inoreader profile.
019dd10blist stream contents
Retrieves the full article data for a chosen feed, folder, or tag stream.
019dd10blist subscriptions
Lists all external feeds that are currently subscribed to your account.
019dd10blist tags
Shows every existing user-created tag and folder in your information system.
019dd10bmark all as read
Changes the read status of every article within a selected stream to marked as read.
019dd10bquick add subscription
Adds a brand new RSS or Atom feed by inputting its specific URL.
019dd10brename tag
Changes the name of an existing tag or folder to something more descriptive.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Inoreader, then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Inoreader. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
The Friction of Information Overload Today
Right now, keeping track of hundreds of feeds means constant context switching. You open Site A for news, then switch to Site B's feed widget, copy the headline, and paste it into your notes. Then you have to manually check if that article is already tagged or filed somewhere else.
With this MCP connected, your AI client handles the entire process. It pulls content from multiple sources using `list_stream_contents` and lets you instantly organize and tag everything in one go. You just get a single, clean output of actionable intelligence.
Inoreader MCP: Full Content Control
You no longer have to manually check the status or list subscriptions across multiple dashboards. Your agent can run `list_subscriptions` and report on everything, or use `get_unread_counts` to give a real-time summary.
The difference is that your AI client manages the entire lifecycle of an idea—from finding it in a feed to tagging it, marking it as read, and knowing exactly where it lives. It’s done.
What you can do with this MCP connector
You're constantly reading stuff—research papers, industry blogs, social media threads. Manually checking those streams is a time sink. This MCP gives your AI client access to hundreds of feeds. You can use it to list all your subscriptions and quickly add new content sources by URL. Beyond just pulling data, you control the structure: rename tags, delete folders, or apply organization labels using edit_tag.
Need to know what's fresh? Get real-time summaries of unread counts across every category via get_unread_counts. The whole thing works through your AI client connected via Vinkius. You don't just read articles; you build an information architecture and keep track of everything important, making sure nothing falls through the cracks.
019dd10b-da38-71af-801f-ddcbf391e94e 
How Inoreader MCP Works
- 1 Subscribe to this MCP and provide your Inoreader Access Token.
- 2 Your AI client authenticates with the platform and pulls a list of available feeds and folders.
- 3 You query the tool to list content, apply tags (e.g., 'Tech'), or check unread counts.
The bottom line is you get natural language control over your entire news archive, letting your agent manage it for you.
Who Is Inoreader MCP For?
This MCP targets knowledge workers who are drowning in information but need structure. It's for the researcher who spends hours manually cross-referencing data points or the content creator who needs to track niche industry trends across dozens of sites.
Uses list_subscriptions and get_unread_counts to monitor competitor activity across multiple industry blogs, focusing only on unread content.
Runs bulk actions using mark_all_as_read after reviewing a batch of articles and uses list_tags to identify recurring themes for new content pillars.
Retrieves specific article contents via list_stream_contents, filtering by keywords, then uses edit_tag to sort the results into 'Actionable' or 'FYI'.
What Changes When You Connect
- Stop manually checking feeds. Instead, use the
list_stream_contentstool to have your agent pull content from dozens of sites in one go. - Never lose an idea again. You can categorize articles instantly by running
edit_tagand sorting them into structured folders like 'Inspiration' or 'To Read Later'. - Know what matters right now. Running
get_unread_countsgives you a single dashboard view of your unread workload, so you prioritize correctly. - Build your knowledge base efficiently. If a critical source goes down, you can quickly add a replacement feed using the
quick_add_subscriptiontool. - Maintain data hygiene by listing all organizational labels with
list_tags, then cleaning up stale folders or renaming them viarename_tag.
Real-World Use Cases
A competitor launch needs tracking.
The agent runs a query to pull articles about 'AI Chips' from three different industry feeds using list_stream_contents. The user then uses the AI to summarize key takeaways and applies the tag 'Competitor Alert' via edit_tag.
A massive backlog of old news needs clearing.
The user identifies a folder containing articles from an expired project. Instead of opening each one, they instruct the agent to run mark_all_as_read, instantly clearing the entire stream's unread count.
Need to consolidate sources.
A new niche topic emerges. The user finds three relevant blogs and uses quick_add_subscription for each, immediately integrating them into their reading list without changing any settings.
Cleaning up an old knowledge vault.
The project is finished. Instead of manually deleting articles, the user runs delete_tag on the 'Old Project' tag across all streams to remove the organizational label while keeping the content for future reference.
The Tradeoffs
Manual Tagging
Reading an article, then having to open a separate tagging interface and manually clicking the tag button. This is slow and requires context switching.
→
Let your agent handle it. After running list_stream_contents for articles from a source, ask your AI client to apply tags automatically using edit_tag. It's faster.
Checking feeds one by one
Needing to know if the 'Finance' feed and the 'Tech' feed both have unread items, forcing multiple manual checks.
→
Use get_unread_counts for each specific stream name. Your agent can execute these calls in sequence and give you a consolidated count report.
Accidental data loss
Thinking that deleting the 'Marketing' folder removes all related articles, causing confusion about where the content went.
→
Be careful. Use delete_tag only if you want to remove the label. The underlying articles remain in place.
When It Fits, When It Doesn't
Use this MCP if your core workflow is about curation and organization. Specifically, use it when you need to check status (via get_unread_counts) or structure content across disparate sources. You must be managing RSS feeds and tags.
Don't use this if:
1. You just need to scrape a single webpage for one-time data; that’s a web scraping tool.
2. You are building a transactional system (like sending emails or booking appointments); you need a messaging or calendar MCP instead.
3. Your goal is simple content transformation (e.g., summarizing text pasted into the chat box). In those cases, your AI client alone handles it.
Common Questions About Inoreader MCP
How do I use `quick_add_subscription` with Inoreader? +
You provide the tool with a valid RSS or Atom feed URL. The MCP then handles adding that new source to your personal reading list, making it immediately available for content retrieval.
Can `list_stream_contents` fetch articles from different sources? +
Yes. You can specify a single feed, but you can also use tags or folders as criteria to pull related article contents across multiple subscriptions into one stream for review.
What is the difference between `edit_tag` and `delete_tag`? +
edit_tag adds or removes labels from articles, keeping them accessible. delete_tag actually deletes the organizational label itself, which doesn't affect the article content.
Does `mark_all_as_read` work across all my feeds? +
No. You must specify the stream or tag you want to clear. It works on a targeted level—you tell it which group of articles needs marking.
How do I check my Inoreader account status using the `get_user_info` tool? +
It returns basic metadata about your connected account, confirming that the access token is valid and active. If you encounter specific authorization or expired token errors, it means the connection needs refreshing; the token itself must be updated in your developer preferences.
If I use the `rename_tag` tool, how does it handle existing tag names or conflicting folder paths? +
The tool validates potential conflicts before making changes. If you try to rename a tag to a name that already exists, it will fail with an error code, preventing any data corruption. Always run list_tags first to check for available names.
When calling `list_stream_contents`, what parameters can I pass to filter for specific content formats, like images or videos? +
You can specify filters beyond just text search. The tool accepts MIME type parameters and source IDs, allowing you to restrict results specifically to articles, images, or other media types within a given feed.
Can `get_unread_counts` provide a comprehensive summary of all my active feeds and folders' unread totals? +
Yes, by default, it aggregates the unread counts across every accessible stream in your account. If you need to limit the count to only a specific set of feeds, pass those feed IDs as an optional scope parameter.
Can I use this to find specific articles across all my subscriptions? +
Yes! Use the list_stream_contents tool with the system stream ID user/-/state/com.google/reading-list. You can then ask the AI to filter or search for specific keywords within the returned articles.
Is it possible to star articles directly from the conversation? +
Absolutely. Use the edit_tag tool and provide the Article ID with the add parameter set to user/-/state/com.google/starred. This will instantly save the article to your Starred folder in Inoreader.
How do I see how many unread articles I have in each folder? +
Run the get_unread_counts tool. It returns a structured list of all your streams (feeds, folders, and tags) along with the precise count of unread items for each.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.