Bring Rss Reader
to LlamaIndex
Learn how to connect Inoreader to LlamaIndex and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Inoreader MCP Server?
Connect your Inoreader account to any AI agent and transform how you monitor news, blogs, and social feeds through natural language control.
What you can do
- Feed Management — List all your subscriptions and quickly add new RSS/Atom feeds by URL.
- Content Extraction — Fetch article contents from specific feeds, folders, or system streams with advanced filtering.
- Organization — List, create, rename, and delete tags or folders to keep your information architecture clean.
- Engagement — Star important articles, mark items as read, or batch-clear entire streams instantly.
- Unread Monitoring — Get real-time summaries of unread counts across all your categorized content.
How it works
1. Subscribe to this server
2. Enter your Inoreader Access Token (found in your developer preferences)
3. Start querying and organizing your knowledge base from Claude, Cursor, or any MCP client
Who is this for?
- Researchers & Analysts — aggregate intelligence from hundreds of sources and filter for specific keywords using AI.
- Content Creators — monitor industry trends and save inspiration directly to tagged folders without leaving your workspace.
- Information Junkies — keep your 'Unread' counts at zero by letting your AI assistant help you prioritize what truly matters.
Built-in capabilities (10)
Articles will remain but the organizational label is removed. Delete a tag or folder
Use "user/-/state/com.google/starred" to star/unstar an item. Add or remove tags from articles (e.g., Starred)
Get the number of unread items per feed/folder
Get Inoreader user information
Use "user/-/state/com.google/reading-list" for all items. Get articles for a specific feed, folder, or tag
List all user subscriptions (feeds)
List all user tags and folders
Mark all items in a stream as read
Subscribe to a new feed by URL
Rename an existing tag or folder
Why LlamaIndex?
LlamaIndex agents combine Inoreader tool responses with indexed documents for comprehensive, grounded answers. Connect 10 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine Inoreader tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Inoreader tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Inoreader, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Inoreader tools were called, what data was returned, and how it influenced the final answer
Inoreader in LlamaIndex
Inoreader and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Inoreader to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Inoreader in LlamaIndex
The Inoreader MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Inoreader for LlamaIndex
Every tool call from LlamaIndex to the Inoreader MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
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.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query Inoreader tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp