Are you the author? Sign in to claim
MCP server for the Podcast Index API — search podcasts, track appearances, monitor trending shows, check feed health
Connect Claude to the Podcast Index API. Search podcasts, track appearances, monitor trends.

The results shown in the demo above are sample data, not real Podcast Index responses.
Built and maintained by Conor Bronsdon for the Chain of Thought podcast production workflow, where it surfaces guest appearances and checks feed health during research. Conor hosts Chain of Thought, a show about AI infrastructure and how practitioners actually build with it. More tools for creators live in ai-tools-for-creators. Find Conor on X at @ConorBronsdon.
Sibling MCP servers:
git clone https://github.com/conorbronsdon/podcastindex-mcp.git
cd podcastindex-mcp
npm install
npm run build
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"podcastindex": {
"command": "node",
"args": ["/path/to/podcastindex-mcp/build/index.js"],
"env": {
"PODCASTINDEX_API_KEY": "your-api-key",
"PODCASTINDEX_API_SECRET": "your-api-secret"
}
}
}
}
Add to your project's .mcp.json:
{
"mcpServers": {
"podcastindex": {
"command": "node",
"args": ["/path/to/podcastindex-mcp/build/index.js"],
"env": {
"PODCASTINDEX_API_KEY": "your-api-key",
"PODCASTINDEX_API_SECRET": "your-api-secret"
}
}
}
}
This server is entirely read-only: every tool declares the MCP tool annotation readOnlyHint: true, so clients know no call mutates anything and can skip write-consent prompts.
| Tool | Description |
|---|---|
search_by_person | Search for episodes where a person appeared as host or guest. Returns matches across all indexed podcasts. |
search_by_term | Full-text search across all podcasts by topic, show name, or keyword. |
search_by_title | Search for podcasts by title. |
podcast_by_feed_url | Look up a podcast by RSS feed URL. Returns feed ID, iTunes ID, categories, last update, and feed health. |
podcast_by_feed_id | Look up a podcast by its Podcast Index feed ID. Returns full metadata. |
podcast_by_itunes_id | Look up a podcast by its Apple Podcasts (iTunes) ID. |
podcast_by_guid | Look up a podcast by its podcast:guid tag value. |
trending_podcasts | Get currently trending podcasts, with optional language and category filters. |
episodes_by_feed_id | Get episodes for a specific podcast by feed ID. |
episode_by_id | Look up a single episode by its Podcast Index episode ID. |
episodes_live | Get episodes that are currently live (actively streaming). |
recent_episodes | Get the most recently published episodes across the entire index. |
recent_feeds | Get the most recently updated podcast feeds across the index. |
recent_new_feeds | Get podcast feeds newly added to the index. |
value_by_feed_id | Get value4value (lightning payment) info for a podcast by feed ID. |
value_by_feed_url | Get value4value (lightning payment) info for a podcast by feed URL. |
categories_list | Get the full list of Podcast Index categories and their IDs. |
stats_current | Get current aggregate statistics for the Podcast Index. |
API failures are mapped to a typed error hierarchy (PodcastIndexError base, with AuthenticationError, RateLimitError, ValidationError, NotFoundError, and ServerError subclasses keyed off HTTP status) in src/errors.ts. Every tool call still returns the same isError: true response shape on failure — the typed hierarchy just makes the message specific to what went wrong (bad credentials vs. rate limiting vs. a malformed request, etc.) instead of a single generic "API error" string.
Once configured, you can ask Claude things like:
Build the project:
npm run build
Watch for changes during development:
npm run watch
src/api-client.tssrc/types.tssrc/tool-handlers.tsnpm run buildIssues and pull requests are welcome. If there is a Podcast Index endpoint you want exposed as a tool, open an issue describing the use case, or follow the steps above and open a PR. Bug reports should include the tool name and the arguments you passed.
This server exists because of the free, open Podcast Index API and its documentation — all tools here are thin wrappers over that API.
The expanded endpoint coverage and typed-error design in this release were inspired by Craig Lawton's podcastindex-mcp-server, an earlier MCP server for the same API. No code from that project was used here; this server's implementation, tool schemas, and error-handling code were written independently against the official API docs.
All views, opinions, and statements expressed on this account are solely my own and are made in my personal capacity. They do not reflect, and should not be construed as reflecting, the views, positions, or policies of Modular. This account is not affiliated with, authorized by, or endorsed by Modular in any way.
MIT
Run analytics queries on ClickHouse — explore schemas, execute SQL, fetch results
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots
Google's universal MCP server supporting PostgreSQL, MySQL, MongoDB, Redis, and 10+ databases