Pocket Casts MCP Server
Connects AI assistants to Pocket Casts accounts for browsing subscriptions, reading episode details, and retrieving transcripts with automatic transcription via AssemblyAI when no native transcript exists.
README
Pocket Casts MCP Server
An MCP server that connects AI assistants to your Pocket Casts account. Browse your subscriptions, read episode details, and retrieve transcripts — with automatic transcription via AssemblyAI when no native transcript exists.
Built with Bun and FastMCP. Deployable to Railway or any Docker host.
Tools
| Tool | Description |
|---|---|
list-podcasts |
List all subscribed podcasts (includes folder UUIDs) |
new-episodes |
Get recent episodes from your subscriptions |
get-episode |
Get details about a specific episode by UUID |
get-transcript |
Get an episode's transcript (falls back to AssemblyAI if none exists) |
check-transcripts |
Check transcript availability across all podcasts or a specific folder |
Setup
Prerequisites
- Bun v1.3+
- A Pocket Casts account (Plus required for API access)
Install and authenticate
bun install
bun run login
The login command will prompt for your Pocket Casts email and password, then save tokens to auth.json.
Configure environment
Create a .env file:
MCP_API_KEY=your-secret-key-here
ASSEMBLYAI_API_KEY=your-assemblyai-key # optional, enables transcription fallback
Run
bun run start
The server starts on port 3001 (override with PORT env var) using HTTP stream transport.
Connecting to an MCP client
Point your MCP client at:
http://localhost:3001/mcp
Authenticate with either:
Authorization: Bearer <MCP_API_KEY>header?api_key=<MCP_API_KEY>query parameter
Deploy to Railway
The included Dockerfile is Railway-ready. Set these environment variables in your Railway project:
| Variable | Required | Description |
|---|---|---|
MCP_API_KEY |
Yes | Bearer token for MCP client auth |
POCKETCASTS_ACCESS_TOKEN |
Yes | From auth.json after login |
POCKETCASTS_REFRESH_TOKEN |
Yes | From auth.json after login |
POCKETCASTS_EXPIRES_AT |
Yes | From auth.json after login |
ASSEMBLYAI_API_KEY |
No | Enables transcription for episodes without native transcripts |
PORT |
No | Railway sets this automatically |
How transcripts work
- Checks for Pocket Casts-generated transcripts first
- Falls back to RSS-sourced transcripts if available
- If neither exists and
ASSEMBLYAI_API_KEYis set, submits the audio URL directly to AssemblyAI for transcription (no file download required)
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.