AI Agent

Podwise provides a CLI client, agent skills, and a local MCP server that let AI agents, LLMs, and automation pipelines fetch structured podcast insights — transcripts, summaries, outlines, Q&A, mind maps, and more — without a browser or human in the loop.

Podwise CLI and MCP access requires a Pro or Enterprise plan.

CLI

The podwise CLI is purpose-built as a tool for AI agents. Install it via Homebrew, script, or binary:


# Homebrew (macOS)
brew install hardhackerlabs/podwise-tap/podwise
 
# Or use the install script
curl -sL https://raw.githubusercontent.com/hardhackerlabs/podwise-cli/main/install.sh | sh

Then authorize and verify:


podwise auth
podwise config show

Agent Skills

Ready-to-use workflows that route your intent automatically:

Workflow	What it does
catch-up	Catch up on missed episodes from podcasts you follow
weekly-recap	Generate a weekly listening recap with highlights
episode-notes	Export episode summaries and highlights to Notion, Obsidian, or Logseq
topic-research	Research a topic across multiple podcast episodes
episode-debate	Challenge and stress-test ideas from an episode
language-learning	Generate Anki flashcards from a transcript
discover	Get personalised podcast recommendations based on your taste
refine-taste	Build your listener profile for personalised outputs

Install with a single command:


npx skills add hardhackerlabs/podwise-cli

Local MCP Server

Want to use Podwise in Claude, ChatGPT, or Cursor without installing the CLI? Connect to the hosted MCP Server at https://mcp.podwise.ai/mcp instead.

The CLI can also run Podwise as a local MCP (Model Context Protocol) server, allowing AI assistants like Gemini CLI, Claude Desktop, and Cursor to launch it and use Podwise tools directly.


podwise mcp

Add to your AI assistant’s config:


{
  "mcpServers": {
    "podwise": {
      "command": "podwise",
      "args": ["mcp"]
    }
  }
}

For full documentation, all available commands, and advanced usage, visit the podwise-cli GitHub repository .