pocketcasts-mcp
Enables AI assistants to search, browse, and manage your Pocket Casts podcast library.
README
Pocket Casts MCP Server
An MCP (Model Context Protocol) server that connects to the Pocket Casts podcast app, allowing AI assistants to search, browse, and manage your podcast library.
Note: This uses the unofficial Pocket Casts API. There is no official public API — this server relies on reverse-engineered endpoints used by community projects.
Prerequisites
- Node.js 18+
- A Pocket Casts account (email & password)
Installation
Remote (npx — no clone required)
Run the server directly without installing anything locally:
npx pocketcasts-mcp
Claude Desktop
Add to your config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"pocketcasts": {
"command": "npx",
"args": ["-y", "pocketcasts-mcp"],
"env": {
"POCKETCASTS_EMAIL": "your@email.com",
"POCKETCASTS_PASSWORD": "your-password"
}
}
}
}
Claude Code
claude mcp add pocketcasts \
-e POCKETCASTS_EMAIL=your@email.com \
-e POCKETCASTS_PASSWORD=your-password \
-s user \
-- npx -y pocketcasts-mcp
The -s user flag makes the server available across all your projects. Omit it to scope to the current project only.
Global install (alternative)
Install once, then reference the command directly:
npm install -g pocketcasts-mcp
Then use pocketcasts-mcp as the command instead of npx -y pocketcasts-mcp in the configs above.
Local (from source)
Clone and build the server yourself:
git clone https://github.com/essoen/PocketCasts-mcp.git
cd PocketCasts-mcp
npm install
npm run build
Claude Desktop
{
"mcpServers": {
"pocketcasts": {
"command": "node",
"args": ["/absolute/path/to/PocketCasts-mcp/dist/index.js"],
"env": {
"POCKETCASTS_EMAIL": "your@email.com",
"POCKETCASTS_PASSWORD": "your-password"
}
}
}
}
Claude Code
claude mcp add pocketcasts \
-e POCKETCASTS_EMAIL=your@email.com \
-e POCKETCASTS_PASSWORD=your-password \
-s user \
-- node /absolute/path/to/PocketCasts-mcp/dist/index.js
Cursor / VS Code
Add to .cursor/mcp.json or .vscode/mcp.json in your project:
{
"mcpServers": {
"pocketcasts": {
"command": "node",
"args": ["/absolute/path/to/PocketCasts-mcp/dist/index.js"],
"env": {
"POCKETCASTS_EMAIL": "your@email.com",
"POCKETCASTS_PASSWORD": "your-password"
}
}
}
}
Or with npx (no local clone needed):
{
"mcpServers": {
"pocketcasts": {
"command": "npx",
"args": ["-y", "pocketcasts-mcp"],
"env": {
"POCKETCASTS_EMAIL": "your@email.com",
"POCKETCASTS_PASSWORD": "your-password"
}
}
}
}
Configuration
The server requires two environment variables:
| Variable | Description |
|---|---|
POCKETCASTS_EMAIL |
Your Pocket Casts account email |
POCKETCASTS_PASSWORD |
Your Pocket Casts account password |
These can be set via:
- The
envblock in your MCP client config (recommended) - Your shell profile (
~/.bashrc,~/.zshrc, etc.) - A
.envfile in your project (if your MCP client supports it)
Security: Never commit files containing your credentials to version control. If using a
.envfile, ensure it is listed in.gitignore. Avoid storing passwords in config files that may be synced or backed up to cloud services.
Available Tools
Discovery
| Tool | Description |
|---|---|
search_podcasts |
Search for podcasts by keyword or title |
get_top_charts |
Get top-ranked podcasts |
get_trending |
Get currently trending podcasts |
get_featured |
Get featured podcasts |
Library
| Tool | Description |
|---|---|
get_subscriptions |
List all subscribed podcasts |
Episodes
| Tool | Description |
|---|---|
get_podcast_episodes |
List episodes for a podcast (sorted newest or oldest) |
get_episode_notes |
Get show notes for an episode |
get_new_releases |
Get new episodes from subscriptions |
get_in_progress |
Get partially-listened episodes |
get_starred |
Get starred/favorited episodes |
get_history |
Get listening history (most recent 100) |
Playback Management
| Tool | Description |
|---|---|
update_playing_status |
Mark episode as unplayed, in_progress, or completed |
update_played_position |
Set playback resume position (in seconds) |
update_starred |
Star or unstar an episode |
Development
git clone https://github.com/essoen/PocketCasts-mcp.git
cd PocketCasts-mcp
npm install
npm run build
npm start
API Reference
This server uses the unofficial Pocket Casts API at api.pocketcasts.com. Endpoints were reverse-engineered by the community. See furgoose/Pocket-Casts for the original documentation.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.