Podwise MCP server
Commit Oct 22, 2026Lets AI agents search podcast episodes, retrieve transcripts, read AI summaries, and perform research across audio content.
Also known as hardhackerlabs/podwise-plugin, podwise-plugin
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 1.0.0
- Last commit
- Oct 22, 2026
- License
- MIT
What is Podwise MCP?
Podwise lets AI agents search podcast episodes, retrieve transcripts, read AI summaries, and perform research across audio content.
Summary generated from the project's README
About Podwise MCP server
Researching podcast content and extracting insights from audio is what Podwise enables for developers using AI agents. By connecting to a remote HTTP server via OAuth 2.0, this tool allows clients like Claude Code, Cursor, and ChatGPT to interact directly with your podcast library. It provides a bridge between conversational AI and audio data, allowing agents to perform complex tasks without requiring manual transcription or note-taking.
The server provides 38 tools categorized into functions such as search, library management, and artifact retrieval. You can use tools like search_episodes to find specific content, get_episode_transcript to pull text, or export_episode_markdown to save summaries to your personal knowledge management system. It also supports advanced workflows like language learning through transcript analysis and enterprise-level audio processing for high-volume requirements. Users must have a Podwise account to authenticate through the browser-based OAuth flow.
What you can do with it
- 1Automated weekly listening recapsAsk your AI agent to generate a summary of the most important highlights from the podcasts you follow each week.
- 2Deep topic research across audioInstruct an agent to investigate a specific subject by searching through multiple podcast episodes for relevant information.
- 3Language learning from transcriptsHave an AI client create study materials like flashcards based on the text of a podcast episode.
- 4Exporting episode notes to MarkdownDirect your agent to convert podcast summaries and highlights into Markdown files for your personal notes.
Written from the project's README. Every use case is checked against a quote from it.
How to install Podwise MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Podwise MCP in Claude Code
$ claude mcp add --transport http podwise-plugin https://mcp.podwise.ai/mcpInstall Podwise MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"podwise-plugin": {
"url": "https://mcp.podwise.ai/mcp"
}
}
}Install Podwise MCP in VS Code
.vscode/mcp.json
{
"servers": {
"podwise-plugin": {
"type": "http",
"url": "https://mcp.podwise.ai/mcp"
}
}
}Install Podwise MCP in VS Code CLI
$ code --add-mcp '{"name":"podwise-plugin","type":"http","url":"https://mcp.podwise.ai/mcp"}'Install Podwise MCP in Codex
$ codex mcp add podwise-plugin --url https://mcp.podwise.ai/mcpInstall Podwise MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.podwise-plugin] url = "https://mcp.podwise.ai/mcp"
Install Podwise MCP in Gemini CLI
$ gemini mcp add -s user --transport http podwise-plugin https://mcp.podwise.ai/mcpInstall Podwise MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"podwise-plugin": {
"url": "https://mcp.podwise.ai/mcp",
"type": "http"
}
}
}Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablehardhackerlabs/podwise-plugin is public and reachablegithub.com/hardhackerlabs/podwise-plugin ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-22github.com/hardhackerlabs/podwise-plugin ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubPodwise Plugin
Turn podcast episodes into AI-powered insights from inside Claude Code, Cursor, Codex and ChatGPT. This plugin bundles the Podwise Agent Skill with the remote Podwise MCP server (https://mcp.podwise.ai/mcp), so installing the plugin wires everything up.
In short: a podcast MCP server for AI agents. Point any MCP client at https://mcp.podwise.ai/mcp and it can search podcasts and episodes, pull a full transcript, read the AI summary, chapters, highlights, Q&A and mind map, ask questions across transcripts, translate an episode, clip key moments, and export notes as Markdown or SRT. The skill teaches your agent how to combine those tools into repeatable workflows.
What's included
| Component | Description |
|---|---|
| Skill | podwise — routes your intent to the right podcast workflow |
| MCP server | Remote HTTP server at https://mcp.podwise.ai/mcp (OAuth) |
Workflows
The skill routes your intent automatically:
| Workflow | What it does |
|---|---|
| catch-up | Catch up on missed episodes from shows you follow |
| weekly-recap | Generate a weekly listening recap with highlights |
| episode-notes | Export episode summaries and highlights to your PKM |
| topic-research | Research a topic across multiple episodes |
| episode-debate | Challenge and stress-test ideas from an episode |
| language-learning | Generate language flashcards from a transcript |
| discover | Get personalised podcast recommendations |
MCP server and tools
Endpoint: https://mcp.podwise.ai/mcp — Streamable HTTP, OAuth 2.0. No API key lives in this repository.
Listed on the official MCP Registry as io.github.hardhackerlabs/podwise (see server.json).
38 tools, grouped:
| Group | Tools |
|---|---|
| Account | get_me |
| Search and discovery | search_episodes, search_podcasts, get_popular_episodes |
| Library and history | list_followed_episodes, list_followed_podcasts, list_podcast_episodes, list_my_episodes, set_podcast_follow, set_episode_read |
| Processing and import | process_episode, import_episode, start_audio_upload, complete_audio_upload |
| Artifacts and Q&A | get_episode, get_episode_summary, get_episode_transcript, ask_podwise, get_ask_history, translate_episode, list_episode_translations |
| Clips | create_clip, get_clip, list_clips, delete_clip, export_clips_markdown, send_clips |
| Export | export_episode_markdown, export_episode_srt, send_episode |
| Enterprise | enterprise_process_audio, enterprise_get_status, enterprise_get_result, enterprise_query_results, enterprise_translate, enterprise_get_translation, enterprise_export, enterprise_get_usage |
Full parameter reference: skills/podwise/references/mcp.md.
Install
Claude Code
/plugin marketplace add hardhackerlabs/podwise-plugin
/plugin install podwise@podwise
Then authenticate the MCP server when prompted (OAuth runs in your browser via /mcp).
Cursor
Open Customize → Plugins → Add → From GitHub Repository and import this repository as a marketplace (use the full URL):
https://github.com/hardhackerlabs/podwise-plugin
Then click Add on podwise and authenticate the MCP server when prompted (Customize → Plugins → podwise → Authenticate).
Once Podwise is listed in the Cursor Marketplace, you can also install it from any agent chat:
/add-plugin podwise
The MCP server alone is also available as a one-click install from cursor.directory.
Codex / ChatGPT
codex plugin marketplace add hardhackerlabs/podwise-plugin
codex plugin add podwise@podwise
Then complete the OAuth flow when prompted.
Other agents (skills only)
If your agent reads skills directly but does not install plugins, install the skill and add the MCP server manually:
npx skills add hardhackerlabs/podwise-plugin
Then add the server to your MCP configuration. Use the transport name your client expects — http for Claude Code-style clients (as in .mcp.json), streamable-http for Agent Plugins clients (as in mcp.json):
{ "mcpServers": { "podwise": { "type": "http", "url": "https://mcp.podwise.ai/mcp" } } }
Usage
Once the plugin is installed and authenticated, just ask. For example:
- "Catch me up on this week's podcast episodes"
- "Summarize this podcast episode: "
- "Research what podcasts say about "
- "Write my weekly listening recap"
- "Make language-learning cards from this episode's transcript"
The skill checks the connection with get_me first, then routes the request to the matching workflow.
Requirements
- A Podwise account. The MCP server uses OAuth 2.0; no API key is stored in this repository.
- Network access to
https://mcp.podwise.ai/mcp. - Some capabilities require a Podwise Pro or Enterprise plan; the
enterprise_*tools are for Enterprise-plan API usage. See podwise.ai for plans.
Remote / SSH note: the host's HTTP MCP OAuth uses a loopback callback, which does not work when the host runs on a machine different from your browser. Use a connection method supported by your host, or see the troubleshooting docs at https://docs.podwise.ai. Do not run third-party proxy commands to work around authentication.
Repository layout
podwise-plugin/ # this repository is the plugin (source: "./")
├── .claude-plugin/
│ ├── marketplace.json # Claude Code marketplace
│ └── plugin.json # Claude Code plugin manifest
├── .codex-plugin/plugin.json # Codex / ChatGPT client manifest
├── .cursor-plugin/
│ ├── marketplace.json # Cursor marketplace
│ └── plugin.json # Cursor plugin manifest
├── .agents/plugins/marketplace.json # Codex marketplace
├── plugin.json # Portable Agent Plugins manifest
├── mcp.json # Remote MCP server config (Agent Plugins, streamable-http)
├── .mcp.json # Remote MCP server config (Claude Code and Codex, http)
├── server.json # MCP registry manifest (official registry, aggregators)
├── skills/podwise/ # The Podwise skill
│ ├── SKILL.md
│ ├── references/
│ ├── workflows/
│ └── agents/openai.yaml
└── assets/
The MCP definition is duplicated as mcp.json (portable Agent Plugins, streamable-http) and .mcp.json (referenced by the Claude Code and Codex manifests, http). Keep the transport type matching each platform.
Brand assets
| Asset | File | Size | Declared in |
|---|---|---|---|
| Logo | assets/logo.png |
1024×1024 PNG | .cursor-plugin/plugin.json (logo), .codex-plugin/plugin.json and plugin.json (interface.logo) |
| Composer icon | assets/composer-icon.png |
256×256 PNG | .codex-plugin/plugin.json and plugin.json (interface.composerIcon), shown in the chat composer |
Brand color is #7948E8.
Privacy and support
- Privacy policy: https://podwise.ai/privacy
- Terms of service: https://podwise.ai/terms
- Support and docs: https://docs.podwise.ai
License
MIT © Podwise
Podwise MCP questions
How do I add Podwise MCP to Claude Code?
Run claude mcp add --transport http podwise-plugin https://mcp.podwise.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Podwise MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I authenticate with Podwise?
Authentication is handled via OAuth 2.0 through your browser when prompted by your MCP client.
Can I export podcast notes?
Yes, you can export episode summaries and highlights as Markdown or SRT files.