How to Use the Feedly MCP in OpenAI Agents SDK

Q: Can my agent organize feeds into specific folders?

Yes, the agent can use listcategories to find your target folders and then run subscribetofeed to drop new RSS feeds directly into those buckets.

Feed Feedly research directly to your OpenAI Agents SDK pipelines with built-in guardrails and zero-config tool discovery.

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 OpenAI Agents SDK

Create your Vinkius account to connect Feedly to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe feed consumption in OpenAI Agents SDK

The `get_stream_contents` tool lets your agent pull raw article data directly into your OpenAI Agents SDK runtime. This is the first step in building a production pipeline where you need to fetch fresh industry news without manual copying. By setting up this integration with the Python SDK, you get built-in safety guardrails that validate every single input before the agent actually triggers the call. You can trace every single fetch operation directly on your OpenAI developer dashboard to see what feeds are hitting your rate limits.

Automated subscription management with handoffs

The `subscribe_to_feed` and `unsubscribe_from_feed` tools give your agent systems the ability to curate their own data sources dynamically. Instead of hardcoding RSS links, your agent evaluates content quality and subscribes to high-signal feeds on the fly. With the OpenAI Agents SDK, you can set up specialized agents that hand off tasks to one another. One agent scans incoming content using `get_article_details`, while a supervisor agent decides whether to invoke `mark_articles_as_read` to keep the queue clean.

Categorization and tagging workflows

The `list_categories` and `list_tags` tools expose your existing Feedly organization structure directly to your agent. Your agent maps incoming articles to your predefined taxonomy without losing the context of your manual setup. This integration runs inside a secure V8 sandbox on Vinkius, meaning your API tokens remain isolated while your MCP tool pipeline processes tags. You get a single, secure endpoint token to handle the entire connection.

Setup guide

Set up Feedly MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Feedly tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Feedly tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Feedly tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Feedly Agent",
            instructions="You have access to Feedly tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install openai-agents first. Initialize the MCPServerStreamableHttp constructor with your Vinkius endpoint URL and pass it to the Agent constructor. The SDK automatically discovers the ten available tools without extra setup.

Yes. You control feed access by configuring your agent's system prompt or using the list_subscriptions tool to let the agent discover only specific sub-sections of your feed catalog.

The SDK relies on your agent's built-in retry logic. When get_stream_contents hits rate limits, the agent handles the API backoff using standard Python exception handling.

Yes, the agent can use list_categories to find your target folders and then run subscribe_to_feed to drop new RSS feeds directly into those buckets.

Your Feedly developer token is stored in the Vinkius vault and never exposed to the OpenAI Agents SDK runtime. The agent only interacts with the MCP tools like get_user_profile through a secure, ephemeral V8 isolate that handles authorization on your behalf.

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