How to Use the Listen Notes MCP in OpenAI Agents SDK

Q: Can the agent fetch specific genres using this setup?

Yes, the agent calls listpodcastgenres to retrieve the full list of available genres and their corresponding IDs. It then passes the selected ID to getbestpodcasts to filter the results.

Build production-ready OpenAI Agents SDK setups that pull real-time podcast data and episode metadata without writing custom API wrappers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Listen Notes MCP to OpenAI Agents SDK

Create your Vinkius account to connect Listen Notes 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 Listen Notes with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query podcast directories directly from OpenAI Agents SDK

`search_podcasts_or_episodes` serves as the entry point for your agent to query the global directory using the "q" parameter. The agent runs searches, parses the matches, and decides whether to pull deeper metadata without you hardcoding the search logic. This direct integration means your OpenAI Agents SDK pipeline gets raw search results directly from the MCP Server. Parsing the JSON payload immediately, the agent passes the structured search results to downstream tasks or summarizes them for the user.

Resolve deep show metadata with agent handoffs

`get_podcast_details` and `get_episode_details` resolve specific show feeds and individual audio files once your search agent identifies a target. Your primary agent can hand off the heavy lifting to a specialized metadata agent that handles these specific calls. The OpenAI Agents SDK handles the coordination, validating that the agent passes a valid ID before executing the tool. You get clean, structured metadata payloads containing publisher info, episode notes, and audio links without worrying about payload corruption.

Track trending topics with an OpenAI MCP Server

`get_trending_podcast_searches` gives your agent immediate access to what listeners are looking for right now. The agent discovers trending terms and automatically triggers deeper searches to build curated recommendation lists. Using `get_curated_podcasts` alongside these trends lets the OpenAI Agents SDK construct highly relevant, context-aware suggestions. The system handles the entire discovery pipeline autonomously, pulling curated lists and matching them against active search trends.

Setup guide

Set up Listen Notes 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 Listen Notes tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Listen Notes 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="Listen Notes Agent",
            instructions="You have access to Listen Notes 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 Listen Notes. 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 Listen Notes 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 Listen Notes MCP in OpenAI Agents SDK

The SDK manages HTTP requests via the streamable HTTP transport, but you must monitor your API key limits. If the API returns a rate limit error, the SDK raises an exception that your agent's error-handling loop can catch and retry.

Yes, you control tool exposure during agent initialization. By configuring the MCP Server streamable parameters, you expose only the specific tools, like `get_best_podcasts`, that your agent needs for its specific task.

Vinkius handles the API authentication for you behind the scenes. You simply configure the MCPServerStreamableHttp endpoint with your Vinkius token, and the SDK connects to the managed MCP Server without exposing raw API keys in your client code.

Yes, the agent calls `list_podcast_genres` to retrieve the full list of available genres and their corresponding IDs. It then passes the selected ID to `get_best_podcasts` to filter the results.

All search queries and metadata payloads pass through an ephemeral V8 sandbox hosted by Vinkius. No search history or podcast IDs are stored on the server after the execution completes, keeping your agent's data footprint completely isolated.

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