How to integrate Listennotes MCP with Pydantic AI

Connect Pydantic AI to Listennotes MCP. Find top tech podcasts from last week, get audience stats for this podcast, and more using natural language, with authentication handled for you.

Listennotes logoListennotes
Api Key

Listennotes is a powerful podcast search engine with a massive global database. Discover, search, and curate podcasts from around the world in seconds.

26 Tools

Introduction

This guide walks you through connecting Listennotes to Pydantic AI using the Composio tool router. By the end, you'll have a working Listennotes agent that can search podcasts and episodes, browse best podcast lists, fetch recommendations, check trending searches, and submit podcast RSS feeds through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Listennotes account through Composio's Listennotes MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

For exact tool slugs and parameter tables, see the tool catalog in the Composio docs.

Also integrate Listennotes with

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Listennotes
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Listennotes workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Listennotes MCP server, and what's possible with it?

The Listen Notes MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Listen Notes account. It provides structured and secure access to podcast and episode information, recommendations, curated lists, audience data, and playlists, so your agent can find episodes by title, retrieve podcast details, discover recommendations, review audience demographics, and access playlists on your behalf.

  • Podcast and episode lookup: Have your agent search for episodes by title, retrieve detailed episode information, or fetch a podcast and its episodes.
  • Podcast discovery: Let the agent retrieve best podcast lists, curated collections, trending searches, related search terms, and typeahead suggestions.
  • Personalized recommendations: Direct your agent to find recommended podcasts or episodes based on a podcast or episode you already know.
  • Audience and publisher research: Instruct your agent to review a podcast's audience demographics or find podcasts associated with a publisher's domain.
  • Playlists and podcast submissions: Have your agent fetch your playlists and their details, submit a podcast feed to the Listen Notes database, or request a podcast's deletion.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Listennotes
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Listennotes
  • MCPServerStreamableHTTP connects to the Listennotes MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Listennotes
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["listennotes"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Listennotes tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
listennotes_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[listennotes_mcp],
    instructions=(
        "You are a Listennotes assistant. Use Listennotes tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Listennotes endpoint
  • The agent uses GPT-5 to interpret user commands and perform Listennotes operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Listennotes.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Listennotes API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Listennotes and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Listennotes
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["listennotes"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    listennotes_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[listennotes_mcp],
        instructions=(
            "You are a Listennotes assistant. Use Listennotes tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Listennotes.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Listennotes through Composio's Tool Router. With this setup, your agent can perform real Listennotes actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Listennotes for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Listennotes action and event your agent gets out of the box.

Post episodes by ids

Retrieves metadata for multiple known podcast episodes by ID in one request.

Create podcast via form data

Retrieves metadata for multiple podcasts by Listen Notes IDs, RSS URLs, Apple Podcasts IDs, or Spotify IDs, with optional latest episodes.

Retrieve curated podcast by id

Retrieves detailed information about a specific curated podcast using its unique identifier.

Fetch best podcasts list

The getBestPodcasts endpoint retrieves a curated list of the best podcasts from the Listen Notes platform.

Retrieve genre list

The GetGenres endpoint retrieves a comprehensive list of available genres within the listennotestest platform.

Get playlists

Retrieves a paginated, sortable list of playlists associated with your Listen Notes account, including basic playlist metadata.

Listen to just listen endpoint

Retrieves a random podcast episode from Listen Notes, with episode metadata and associated podcast information.

Get podcast audience by id

Retrieves audience demographics for a podcast by ID, including audience distribution by region when available.

Get curated podcasts

Retrieves a page of curated podcast lists from Listen Notes, with list metadata and a preview of up to five podcasts in each list.

Retrieve episode by id

Retrieves detailed information about a specific episode using its unique identifier.

Fetch Podcast Details And Episodes

Retrieves detailed metadata for a podcast by ID along with a page of its episodes.

Fetch podcast languages

Retrieves the list of supported podcast languages from Listen Notes for use in content filtering.

Get podcast domains by name

Retrieves a list of podcasts associated with a specified domain name.

Get episode recommendations by id

Retrieves a list of recommended podcast episodes based on a specific episode ID.

Get podcast recommendations by id

Retrieves a list of podcast recommendations based on a specified podcast ID.

Fetch related searches data

Retrieves search terms related to a supplied search query.

Fetch Supported Regions

Retrieves information about available regions in the listennotestest platform.

Retrieve trending searches

Retrieves a list of currently trending search terms related to podcasts.

Search Episode Titles

Searches for podcast episodes by title, optionally restricted to a specified podcast.

Search operation endpoint

Searches Listen Notes for episodes, podcasts, or curated podcast lists using a text query.

Fetch Playlist Info

Retrieves a playlist by ID, including its metadata and a sortable, paginated list of episode, custom audio, or podcast items.

Post podcast rss by id

Requests an RSS feed refresh for a podcast by ID and returns the refresh status and last refresh timestamp when available.

Delete podcast by id

Requests deletion of a podcast by ID, optionally supplying a reason, and returns the request status.

Spell check retrieval

Checks the spelling of a supplied search term and returns misspelled tokens, suggestions, and corrected text with HTML formatting.

Submit podcast rss url

Submits a podcast RSS feed to the Listen Notes database, optionally providing an email for acceptance notifications; submission does not guarantee inclusion.

Get typeahead suggestions

Retrieves typeahead search-term suggestions for a query, with optional podcast and genre suggestions.

FAQ

Frequently asked questions

Start with Listennotes.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Listennotes tool your agent needs.Free to start.

Start building