How to Use the Feedly MCP in LangChain

Q: How do I initialize the Feedly MCP Server inside a LangChain agent?

Install langchain-mcp-adapters and use MultiServerMCPClient to connect to the Vinkius endpoint. Call client.gettools() to load all 12 tools and pass them directly to your agent runner.

Q: How does LangChain manage state across multiple Feedly tool calls?

LangChain is stateless by default, but you can use client.session() to preserve context. This keeps your active boards from listboards accessible across different steps of your curation chain.

Q: Can I search for new RSS feeds using Feedly and LangChain?

Yes, your agent can use searchfeeds to find new sources based on user queries and immediately add them to your tracking pipelines.

Run multi-step news curation chains in LangChain using your live Feedly subscriptions and boards.

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 MCP Server tools for automated intelligence

Stop writing manual cron jobs to pull RSS feeds. This Feedly MCP Server lets your LangChain agent fetch raw articles from `get_stream_contents` and pass them to downstream nodes in a single run. You get direct access to your curated feeds without building custom API wrappers. LangChain coordinates the sequence of tool calls based on live outputs. The agent checks your collections with `list_collections`, identifies new articles, and feeds them into your processing pipeline instantly.

Trace and debug feed processing in LangSmith

Complex ingestion pipelines break when feeds format data differently. This Feedly MCP Server allows LangChain to monitor every call to `get_entry` and `get_tag_contents` through LangSmith, showing you the exact payload size and token cost. When an article fails to parse, you can pinpoint whether the error happened during the `get_board_contents` fetch or during the LLM summary step. No more guessing why your feed parser stalled.

Multi-server aggregation with LangChain

Your news monitoring does not live in a vacuum. This Feedly MCP Server lets you combine this Feedly integration with database or Slack tools in the same execution graph. After finding matches with `search_topics`, your agent can automatically update your internal knowledge base. You can also run `mark_as_read` to keep your inbox clean without leaving your terminal.

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-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

Install `langchain-mcp-adapters` and use `MultiServerMCPClient` to connect to the Vinkius endpoint. Call `client.get_tools()` to load all 12 tools and pass them directly to your agent runner.

Yes, you should configure your LangChain runnable with retry logic. When calling `get_stream_contents` on massive feeds, the framework handles backoff so you do not hit API limits.

LangChain is stateless by default, but you can use `client.session()` to preserve context. This keeps your active boards from `list_boards` accessible across different steps of your curation chain.

Yes, your agent can use `search_feeds` to find new sources based on user queries and immediately add them to your tracking pipelines.

Vinkius runs the connector in a secure sandbox. Your Feedly credentials and the RSS streams processed by your LangChain runnable are never stored or exposed to external networks.

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