Connect PodKit via MCP
PodKit ships a Model Context Protocol server so AI agents can call podcast search, metadata, chapters, and transcripts as tools — using your PodKit API key, metered against the same plan quota as the REST API.
The MCP endpoint is https://podkitapp.com/mcp (Streamable HTTP). Authenticate with your API key in the
x-api-key header. Don't have a key? Get one free.
Listed in the official MCP registry as com.podkitapp/podkit.
Claude Code
claude mcp add --transport http podkit https://podkitapp.com/mcp \
--header "x-api-key: YOUR_PODKIT_KEY"Claude Desktop (or any client via mcp-remote)
Add to your claude_desktop_config.json:
{
"mcpServers": {
"podkit": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://podkitapp.com/mcp", "--header", "x-api-key:${PODKIT_KEY}"],
"env": { "PODKIT_KEY": "YOUR_PODKIT_KEY" }
}
}
}Available tools
| Tool | What it does |
|---|---|
search_podcasts | Search podcasts by keyword. Returns normalized podcast metadata; each result’s `id` is the iTunes/Apple collection id you pass to get_podcast. |
get_podcast | Get a podcast and a page of its episodes (newest first) by iTunes id. Each returned episode includes an `id` — pass it to get_episode, get_episode_chapters, or get_episode_transcript. |
get_episode | Get a single episode by its PodKit episode id, with parent podcast info. |
get_episode_chapters | Get an episode’s chapters (podcast:chapters) as normalized JSON. |
get_episode_transcript | Get an episode’s transcript (JSON/VTT/SRT/text) as normalized segments + text. |
Each tool returns the same normalized JSON as the corresponding REST endpoint, and each tool call counts as one request against your monthly quota (discovery/handshake calls are free). See the full schemas in the REST docs.
New to agent setups? Follow the tutorial: Building an AI agent that can search and summarize podcasts.