How to Use the Feedly MCP in OpenAI Agents SDK

Q: Does the OpenAI Agents SDK support caching tools for Feedly?

Yes, you should set cacheToolsList=True during initialization. This prevents your script from querying the server schema on every single run, speeding up tool calls like listtags.

Q: How do I handle agent handoffs when parsing heavy feeds over an MCP connection?

Designate one agent to fetch feed IDs with listcollections. That agent then hands off the specific feed ID to a secondary agent tasked with running getstreamcontents for deep analysis.

Run your OpenAI Agents SDK pipelines with live market intelligence by connecting this Feedly MCP Server directly to your agent network.

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

Automated curation with OpenAI Agents SDK guardrails

Your production agents need clean data without wasting context window space on duplicate articles. This MCP integration lets you spin up a specialized researcher agent that calls `list_collections` to map your industry feeds, then hands off the actual content extraction to a writer agent. By setting up input filters in your Python code, you prevent the model from pulling irrelevant posts. You can track every single call to `get_stream_contents` directly inside your OpenAI developer dashboard. This setup ensures that if an agent tries to pull hundreds of unread articles, your guardrails catch the excessive token usage before it hits your billing limit.

Target key market signals using native board tools

Stop letting your agents guess which articles matter. By exposing `list_boards` and `get_board_contents` to your OpenAI Agents SDK setup, you let your MCP Server focus strictly on human-curated content. The agent looks at what your team already saved, processes those specific entries, and ignores the rest of the noise. This targeted approach keeps your system highly efficient. Instead of scanning entire RSS feeds, the model retrieves the exact text of a curated entry using `get_entry` and routes it to your analytical pipelines.

Clean write-backs for your tracking pipelines

Keep your reading lists clean without manual intervention. Your OpenAI Agents SDK agents can automatically clear out processed items by calling `mark_as_read` once they finish analyzing a post. This prevents the same article from showing up in the next hourly run of your ingestion script. We recommend using `cacheToolsList=True` in your Python initialization to keep these frequent write-backs fast. This keeps your agent execution loop tight, saving precious seconds on every run.

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

You pass your developer token to Vinkius, which handles the auth handshake securely. Then, you simply point your `MCPServerStreamableHttp` client to the Vinkius endpoint, allowing your agent to call `get_profile` instantly.

Yes, your agent can search for new sources. The model invokes the `search_feeds` tool to find relevant RSS feeds and returns them directly to your Python pipeline.

Yes, you should set `cacheToolsList=True` during initialization. This prevents your script from querying the server schema on every single run, speeding up tool calls like `list_tags`.

Designate one agent to fetch feed IDs with `list_collections`. That agent then hands off the specific feed ID to a secondary agent tasked with running `get_stream_contents` for deep analysis.

Your developer token is isolated in an ephemeral V8 sandbox. The server only reads the specific feeds, articles, and boards returned by `get_subscriptions` and never stores your raw data on disk.

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