How to Use the Inoreader MCP in LangChain

Q: Can I use LangChain to filter my Inoreader feeds?

Yes, you can. By passing the output of liststreamcontents into a prompt, your agent can summarize or filter articles based on your specific criteria.

Build custom content pipelines in LangChain by chaining Inoreader API calls for automated feed processing and real-time filtering.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inoreader MCP to LangChain

Create your Vinkius account to connect Inoreader to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Inoreader with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate feed ingestion with LangChain

Connect your agents to live news sources using `list_subscriptions` and `quick_add_subscription`. You can pull fresh content directly into your chains to avoid manual monitoring. Your agent parses the output of `list_stream_contents` to decide which articles require immediate action. It keeps your data flow moving without human intervention.

Manage content organization via LangChain

Control your reading environment by using `edit_tag` and `rename_tag` to categorize incoming data. This keeps your feed structure tidy as your agent processes massive volumes of information. Use `list_tags` to retrieve your current folder structure before making changes. It ensures your logic stays synced with your actual Inoreader setup.

Track read states in LangChain agents

Keep your inbox clean by calling `mark_all_as_read` once your agent finishes processing a batch of articles. It prevents duplicate work by clearing out processed items immediately. Check your progress with `get_unread_counts` to see what remains. This provides the necessary feedback loop for your agent to prioritize remaining tasks.

Setup guide

Set up Inoreader MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Inoreader tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "inoreader-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Inoreader transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Inoreader now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Inoreader MCP in LangChain

Yes, you can. By passing the output of `list_stream_contents` into a prompt, your agent can summarize or filter articles based on your specific criteria.

The MCP server acts as a bridge. Your agent requests data from Inoreader, which sends back the JSON response for your chain to process.

Your data stays local to your execution environment. The MCP server only facilitates the requested operations like `edit_tag` or `list_subscriptions`.

It handles them as fast as the API allows. You should implement your own logic to manage rate limits if you process thousands of items.

The MCP server is stateless. You simply reconnect and re-run your last tool call to resume your feed management.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python