Connect AI assistants with MCP

Use Jellypod from Claude, ChatGPT, and other AI assistants.

The Jellypod MCP server lets an AI assistant create and manage content in your library, with your plan limits and credit rates. On Free the assistant can create and preview; rendering, downloading and publishing need the free trial or a paid plan, as in Studio.

Connect

Add this remote server to your client, then sign in to Jellypod when it asks. The connection uses your current library and permissions.

URL:       https://mcp.jellypod.com/mcp
Transport: Streamable HTTP
Auth:      OAuth

Clients that cannot complete OAuth send a Jellypod API key as a bearer header:

Authorization: Bearer YOUR_API_KEY

Open Settings, then Connectors.
Click Add custom connector and paste the URL.
Click Connect and approve access.

On the web, in Apps & Connectors, open Advanced settings and turn on Developer mode.
Add a new app with the URL and OAuth authentication.
Approve access.

claude mcp add --transport http jellypod https://mcp.jellypod.com/mcp

Then run /mcp, select Jellypod and sign in.

codex mcp add jellypod --url https://mcp.jellypod.com/mcp

A browser window opens to sign in.

Add the MCP Client by Zapier with the URL, transport Streamable HTTP, OAuth off, and your API key as the bearer token.

Add an MCP Client node with the URL, transport HTTP Streamable and Bearer Auth, using your API key as the credential.

In Marketplace, add a custom remote MCP plugin with the URL, then sign in with OAuth or use an API key as the bearer token. See the Grok Bot guide.

Add the URL as a remote Streamable HTTP server. Use OAuth if the client supports it, otherwise a bearer API key.

Find setup steps and API keys in Studio

Click your avatar at the bottom of the Studio sidebar and choose Developers. Settings → Integrations has copy-and-paste setup for each client. Settings → API keys is visible only to administrators and members allowed to manage API keys.

What it can do

Read Podcasts, Episodes, Videos, Shorts and existing Voiceovers, and find saved Characters, built-in Voices and built-in video styles.
Create and update Podcasts and Characters.
Generate Episodes, Videos and Shorts from a prompt or a finished script.
Render a Video, Short or Voiceover again, or export an Episode’s audio or video, without regenerating narration or spending credits.
Update titles, descriptions, captions and watermark position.
Publish, schedule, reschedule and unpublish Episodes.
Create, edit, list and delete Automations.
Permanently delete a Podcast, Episode, Video, Short or Voiceover when you ask it to.
Send feedback about the connector to Jellypod.

For Episodes, Videos and Shorts, prompt writes new narration using any attached Sources as reference material. To keep finished narration word for word, use script and assign its speakers to saved Characters.

A client that supports MCP Apps plays content inline; others get a Listen or Watch link. See the tool reference for names and arguments, and the agent guide for idempotency, polling and retries.

What it cannot do

Accept files. Research material is limited to public webpage or YouTube URLs and plain text the client already holds, such as text it extracted from a file. No file uploads, local paths, private URLs or saved Source IDs. To give Jellypod the original file, use Studio or the Jellypod API.
Create Voiceovers, edit production, or manage the account. Voiceover creation, production editing, analytics, voice cloning, Brand Kits, billing, team management and account settings stay in Studio or, where documented, the API.

Defaults to know

New Podcasts are private, and publishing an Episode does not make its Podcast public.
Episodes stay drafts unless auto_publish is true, which the assistant should use only when you ask it to publish.
A failed generation cannot be retried in place through MCP. For Videos, Shorts and Voiceovers, retry the existing item in Studio or the API first. Starting over through MCP is a new credit-bearing generation. See what a failed generation costs.