New course: Agentic AI for Python Devs

Talk Python to Me MCP Server

Model Context Protocol API for AI Assistants

Overview

The Talk Python to Me podcast provides an MCP (Model Context Protocol) server that allows AI assistants to query podcast episodes, guests, transcripts, and more. MCP is an open standard created by Anthropic for connecting AI models to external tools and data sources.

Server Information

Server Name talk-python-mcp
Version 1.0.0
Endpoint https://talkpython.fm/api/mcp
Discovery URL https://talkpython.fm/.well-known/mcp.json
Transport Streamable HTTP (JSON-RPC 2.0)
Authentication None (public, read-only data)

Available Tools

The following tools are available through this MCP server:

search_episodes

Search Talk Python to Me podcast episodes by keyword. Returns matching episodes with title, description, and URL.

Parameters
Name Type Required Description
query string Yes Search query (keywords to find in episode titles and descriptions)
limit integer No Maximum number of results to return

search_guests

Search podcast guests by name. Returns matching guests with their names and IDs.

Parameters
Name Type Required Description
query string Yes Search query (guest name or partial name)
limit integer No Maximum number of results to return

get_episode

Get full details for a specific podcast episode by its show ID. Returns title, description, published date, duration, and URL.

Parameters
Name Type Required Description
show_id integer Yes The episode show ID (e.g., 400 for episode #400)

get_episodes

Get a list of all podcast episodes with their show IDs and titles. Useful for browsing available episodes before looking up specific details.

No parameters required

get_guests

Get a list of all podcast guests with their names, IDs, and episode appearances. Guests are sorted by number of appearances (most popular first). Useful for browsing available guests and seeing which episodes they appeared on.

No parameters required

get_guest_by_id

Get detailed information about a specific guest by their ID. Returns name, bio, and picture URL.

Parameters
Name Type Required Description
guest_id integer Yes The guest ID

get_transcript_for_episode

Get the full transcript text for a podcast episode. Returns the plain text transcript of the conversation.

Parameters
Name Type Required Description
show_id integer Yes The episode show ID

get_transcript_vtt

Get the transcript for a podcast episode in WebVTT format. WebVTT includes timestamps for each segment, useful for creating subtitles or syncing with audio.

Parameters
Name Type Required Description
show_id integer Yes The episode show ID

get_recent_episodes

Get the most recently published podcast episodes. Returns episodes sorted by publication date (newest first).

Parameters
Name Type Required Description
limit integer No Number of recent episodes to return

Usage Example

To use this MCP server with an AI assistant that supports MCP (like Claude), configure it to connect to the endpoint URL using HTTP POST with JSON-RPC 2.0 format.

Initialize Connection

POST https://talkpython.fm/api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "initialize",
  "params": {
    "clientInfo": {
      "name": "your-client",
      "version": "1.0.0"
    }
  }
}

List Available Tools

POST https://talkpython.fm/api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/list",
  "params": {}
}

Call a Tool

POST https://talkpython.fm/api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 3,
  "method": "tools/call",
  "params": {
    "name": "search_episodes",
    "arguments": {
      "query": "FastAPI",
      "limit": 5
    }
  }
}

Response Format

Tool responses follow the MCP content format:

{
  "jsonrpc": "2.0",
  "id": 3,
  "result": {
    "content": [
      {
        "type": "text",
        "text": "Found 5 episode(s) matching \"FastAPI\":\n\n..."
      }
    ],
    "isError": false
  }
}

Learn More

For more information about the Model Context Protocol, visit the MCP documentation.

Talk Python's Mastodon Michael Kennedy's Mastodon