Listen Notes connector for AI agents

Tools your podcast research agent reaches for on Listen Notes, scoped per user.

CALL ANY TOOL

23 tools for podcast search in Listen Notes: search podcasts and episodes, get episode and podcast metadata, find recommendations, browse best podcasts and curated lists, and suggest search terms.

listennotes_get_curated_list

List get curated

Get one curated podcast list with full metadata for every podcast in it. Same data as listennotes.com/curated-podcasts. Returns id, title, description, source_url, source_domain, pub_date_ms, total and podcasts (id, title, publisher, description, listen_score and other metadata). Use listennotes_get_curated_list once you have a list ID. Use listennotes_list_curated_lists or listennotes_search with type curated to find list IDs.

Parameters

Name

Type

Required

Description

string

Required

Curated list ID, from listennotes_list_curated_lists or a listennotes_search result with type curated. Example: SDFKduyJ47r.

listennotes_get_episode

Get episode

listennotes_get_episode_recommendations

Get episode recommendations

listennotes_get_episodes_batch

Batch get episodes

listennotes_get_playlist

Get playlist

listennotes_get_podcast

Get podcast

listennotes_get_podcast_audience

Get podcast audience

listennotes_get_podcast_recommendations

Get podcast recommendations

listennotes_get_podcasts_batch

Batch get podcasts

listennotes_get_random_episode

Get random episode

listennotes_list_best_podcasts

List best podcasts

listennotes_list_curated_lists

List curated lists

listennotes_list_genres

List genres

listennotes_list_languages

List languages

listennotes_list_playlists

List playlists

listennotes_list_podcasts_by_domain

List podcasts by domain

listennotes_list_regions

List regions

listennotes_list_related_searches

List related searches

listennotes_list_trending_searches

List trending searches

listennotes_search

Run a full-text search across podcast episodes, podcasts or curated podcast lists, with filters for genre, language, region, audio length, publish date and specific podcasts. Returns total, count, next_offset and results: episodes (id, title, description, audio URL, length, pub_date_ms, parent podcast), podcasts (id, title, publisher, total_episodes, listen_score) or curated lists. Matches are highlighted in the *_highlighted fields. The FREE plan returns at most 30 results per query (offset below 30); PRO allows 300. Use listennotes_search for keyword or topic search. Use listennotes_search_episode_titles to find one episode by its exact title, and listennotes_typeahead for autocomplete suggestions.

Parameters

Name

Type

Required

Description

string

Required

Search term, such as a person, place or topic. Wrap it in double quotes for an exact-phrase match; otherwise matching is fuzzy. Example: star wars.

episode_count_max

integer

Optional

Maximum number of episodes a podcast may have. Applies only when type is podcast. Example: 500.

episode_count_min

integer

Optional

Minimum number of episodes a podcast must have. Applies only when type is podcast. Example: 50.

genre_ids

string

Optional

Comma-separated genre IDs to search within; omit for all genres. Get IDs from listennotes_list_genres. Applies to episode and podcast searches. Example: 68,82.

interviews_only

integer

Optional

Set to 1 to return only podcasts that have guest interviews. Applies only when type is podcast. Needs a PRO or ENTERPRISE plan. One of: `0`, `1`.

language

string

Optional

Only return results in this language, by name as listed by listennotes_list_languages. Applies to episode and podcast searches. Example: English.

len_max

integer

Optional

Maximum audio length in minutes. For type episode it filters episode length; for type podcast it filters the podcast's average episode length. Example: 30.

len_min

integer

Optional

Minimum audio length in minutes. For type episode it filters episode length; for type podcast it filters the podcast's average episode length. Example: 10.

ncid

string

Optional

Comma-separated podcast IDs (up to 5) to exclude from episode results. Applies only when type is episode. Example: 25212ac3c53240a880dd5032e547047b.

ocid

string

Optional

Comma-separated podcast IDs (up to 5) to limit episode results to. Applies only when type is episode. Example: 4d3fe717742d4963a85562e9f84d8c79.

offset

integer

Optional

Number of results to skip, for pagination. Pass next_offset from the previous response. FREE plans can page only up to offset 29, PRO up to 299. Example: 10.

only_in

string

Optional

Comma-separated fields to search in: any of title, description, author and audio. Omit to search all fields. Use title,author for better podcast-name matches. Example: title,description.

page_size

integer

Optional

Number of results per page, from 1 to 10. The API default is 10. Example: 5.

published_after

integer

Optional

Only return items published after this time, as a Unix timestamp in milliseconds. Must be earlier than published_before when both are set. Example: 1580172454000.

published_before

integer

Optional

Only return items published before this time, as a Unix timestamp in milliseconds. Must be later than published_after when both are set. Example: 1700000000000.

region

string

Optional

Only return results from this region, by country code as listed by listennotes_list_regions. Applies to episode and podcast searches. Example: us.

safe_mode

integer

Optional

Set to 1 to exclude podcasts or episodes with explicit language; 0 (the default) keeps them. One of: `0`, `1`.

sort_by_date

integer

Optional

Set to 1 to sort by publish date, newest first; 0 (the default) sorts by relevance. One of: `0`, `1`.

sponsored_only

integer

Optional

Set to 1 to return only podcasts that have sponsors. Applies only when type is podcast. Needs a PRO or ENTERPRISE plan. One of: `0`, `1`.

type

string

Optional

What to search: episode (the default), podcast, or curated (curated lists of podcasts). One of: `episode`, `podcast`, `curated`.

unique_podcasts

integer

Optional

Set to 1 to keep only one episode per podcast in the results. Applies only when type is episode. One of: `0`, `1`.

update_freq_max

integer

Optional

Maximum hours between a podcast's new episodes. For weekly shows use 192 here with update_freq_min 144. Applies only when type is podcast. Example: 192.

update_freq_min

integer

Optional

Minimum hours between a podcast's new episodes. For weekly shows use 144 here with update_freq_max 192. Applies only when type is podcast. Example: 144.

listennotes_search_episode_titles

Search episode titles

listennotes_spellcheck

Spellcheck

listennotes_typeahead

Typeahead

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Listen Notes tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["listennotes"], toolNames: [
    "listennotes_search",
    "listennotes_get_episode",
    "listennotes_get_podcast_recommendations"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find recent episodes about AI agents in healthcare and recommend similar podcasts" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["listennotes"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find recent episodes about AI agents in healthcare and recommend similar podcasts" }],
  tools,
});

// Execute the tool call with the user's vaulted Listen Notes API key
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["listennotes"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find recent episodes about AI agents in healthcare and recommend similar podcasts" }],
  tools,
});

// Tool call runs with the user's vaulted Listen Notes API key
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["listennotes"] }, pageSize: 100,
});

const agent = new Agent({
  name: "podcast_research_agent",
  model: "gemini-2.5-pro",
  instruction: "Listen Notes tools scoped to this user",
  tools,
});

await agent.run("Find recent episodes about AI agents in healthcare and recommend similar podcasts");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Listen Notes tool. Click to copy, paste into your agent, done.

Copy the prompt

Copied

Search for episodes about vector databases published this year.

Copy the prompt

Copied

Find episode titles that mention agentic workflows on this podcast.

Copy the prompt

Copied

Show what people are searching for on Listen Notes right now.

Podcasts and episodes

Copy the prompt

Copied

Get the metadata and latest episodes for this podcast.

Copy the prompt

Copied

Show the audience breakdown by country for this podcast.

Copy the prompt

Copied

Get the transcript of this episode.

Discovery

Copy the prompt

Copied

List the best technology podcasts in the US.

Copy the prompt

Copied

Find podcasts similar to this one.

Copy the prompt

Copied

List the podcasts published under npr.org.

SEE HOW AUTH WORKS

Each user connects their own Listen Notes API key once, and Scalekit sends it with every call. Keys stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Listen Notes

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Listen Notes

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Listen Notes

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Listen Notes

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other search and media connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Listen Notes API key looks fine in a demo. In production every search looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared key
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Listen Notes today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Listen Notes as the user or through a shared key?

As the user. Each user connects their own Listen Notes API key once, and Scalekit sends it with every call. Audit logs attribute every search and lookup to that user, not a shared service account.

Where is the Listen Notes API key stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. To rotate it, the user reconnects with a new API key. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Listen Notes?

Yes. All 23 Listen Notes tools are read-only, so the agent can search and read podcast data but cannot change anything. Filter by tool name in listScopedTools to narrow it further, for example to listennotes_search and listennotes_get_episode. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Listen Notes access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Do any Listen Notes tools need a paid plan?

Yes, a few. listennotes_get_episodes_batch, listennotes_get_podcasts_batch, listennotes_list_related_searches, and listennotes_spellcheck need a Listen Notes PRO or ENTERPRISE plan. Search, single podcast and episode lookups, recommendations, and curated lists carry no plan note.