How to Use the Feedly MCP in LangChain

Q: How do I feed Feedly stream content into a LangChain agent?

Use the getstreamcontents tool within your agent's toolset. The agent will fetch the latest articles from your specified stream and pass the text directly into the next chain step.

Q: Can LangChain automatically manage my Feedly subscriptions?

Yes, your agent can use subscribetofeed and unsubscribefromfeed to curate your sources. You can program the chain to follow new sources based on topics found in your current reading list.

Q: Can I filter Feedly articles by tags using LangChain?

Yes. Your agent can call listtags to find your custom organization labels, then filter the articles pulled via getstreamcontents to match those specific tags.

Build multi-step reasoning chains in LangChain that monitor, fetch, and organize your Feedly streams on autopilot.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Feedly MCP to LangChain

Create your Vinkius account to connect Feedly 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 Feedly with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Feedly ingestion with LangChain agents

By exposing `get_stream_contents` and `get_article_details`, this server connects your Feedly account directly to your LangChain ReAct agents. Your agent pulls raw article data and feeds it directly into your prompt templates. This is not just a static reader. It is an active observer that decides when to pull full text based on titles. LangChain coordinates this flow by feeding the output of `list_subscriptions` directly into downstream summarization steps. You do not write glue code. The agent inspects your categories, grabs the relevant streams, and updates your read status using `mark_articles_as_read` in a single run.

Trace every Feedly tool call with LangSmith

This server integrates with LangSmith to trace latency, token use, and tool payloads for every single API call, including `get_feed_metadata`. Debugging complex RSS retrieval chains is a nightmare without visibility. You see exactly why an agent chose to call a specific tool instead of pulling the entire stream. When your LangChain pipeline fails because a feed is rate-limited, the trace points to the exact tool call. This visibility ensures you can fine-tune your agent's decision-making logic without guessing what happened behind the scenes.

Build multi-server chains for deep research

By exposing `list_subscriptions` alongside database tools, this server lets your LangChain agent build multi-server chains. Don't limit your agent to a single source of truth. Combine this Feedly integration with database and vector store tools using a MultiServerMCPClient. Setup is straightforward. Initialize the adapter, call `get_tools()`, and pass them to your agent executor. The framework handles the session state, allowing your agent to manage feeds with `subscribe_to_feed` and `unsubscribe_from_feed` based on your research goals.

Setup guide

Set up Feedly 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 Feedly 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({
    "feedly-alternative-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 Feedly 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 Feedly. 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 Feedly 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 Feedly MCP in LangChain

Use the `get_stream_contents` tool within your agent's toolset. The agent will fetch the latest articles from your specified stream and pass the text directly into the next chain step.

Yes, your agent can use `subscribe_to_feed` and `unsubscribe_from_feed` to curate your sources. You can program the chain to follow new sources based on topics found in your current reading list.

This server returns standard API error codes when rate limits are hit. You should configure your LangChain runnable with retry logic or exponential backoff to handle these limits gracefully.

Yes. Your agent can call `list_tags` to find your custom organization labels, then filter the articles pulled via `get_stream_contents` to match those specific tags.

Your developer tokens and fetched article contents are processed inside an isolated V8 sandbox on Vinkius. No data is stored on our servers, keeping your personal subscription list and API keys completely private.

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

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript