Read shows, episodes, media and download analytics; update episode text in Captivate. For podcasters who host and grow shows on Captivate. Hosted by usefulapi — connect from Claude, ChatGPT, Cursor, or any MCP client.
Team and Enterprise: an Owner adds the connector for the organization first.
Run this command, then run /mcp in Claude Code to log in:
Add to Cursor or add this to ~/.cursor/mcp.json:
{
"mcpServers": {
"captivate": {
"url": "https://captivate.usefulapi.io/mcp"
}
}
}Add to VS Code or add this to .vscode/mcp.json:
{
"servers": {
"captivate": {
"type": "http",
"url": "https://captivate.usefulapi.io/mcp"
}
}
}No Add custom MCP server option? It depends on your account or workspace settings: see OpenAI's guide.
Run these commands. The second one opens the login page:
Other MCP clients (Windsurf, Cline, Zed and more): add the URL as a remote MCP server (Streamable HTTP). The client then opens the login page in your browser. Do not add an Authorization header: see Before you connect.
Read the overview, average, total and monthly downloads of a podcast.
captivate_get_overview_analytics captivate_get_average_analytics captivate_get_monthly_analytics
Read the all-time and monthly downloads of one episode.
captivate_get_episode_total_analytics captivate_get_episode_monthly_analytics captivate_get_episode_overview_analytics
List the scheduled episodes and the episodes of a show.
captivate_list_user_shows captivate_list_scheduled_episodes captivate_list_episodes
Update the text of an episode, for example the title or the show notes.
Changes data · captivate_get_episode captivate_update_episode
Read the RSS feed URL and the media files of a show.
captivate_get_show_feed captivate_list_show_media captivate_get_media
The login page asks for your Captivate user ID and Captivate API token.
Find both in your Captivate dashboard, in the API section of your user settings. They are used only to call the API for you and to derive a private account id.
Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Captivate user ID and Captivate API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
Turn on the Captivate connector, then ask in plain words. The AI picks the tools.
| Tool | Type | What it does |
|---|---|---|
captivate_get_user | read | Get a user Get a Captivate user profile by user id (the id shown in the dashboard API section). Captivate API: GET /users/{id}. |
captivate_list_user_shows | read | List a user's shows List the podcasts (shows) a user can access in any role. Good first call to find show ids. Captivate API: GET /users/{id}/shows. |
captivate_get_show | read | Get a show Get a podcast show by id: title, description, categories, artwork, status and settings. Captivate API: GET /shows/{id}. |
captivate_get_show_feed | read | Get a show RSS feed URL Get the public RSS feed URL of a show. Captivate API: GET /shows/{id}/feed. |
captivate_list_episodes | read | List episodes of a show List the episodes of a show with their status, publish date, titles and shownotes, plus a total count. Captivate API: GET /shows/{id}/episodes. |
captivate_list_scheduled_episodes | read | List scheduled episodes List the episodes of a show that are scheduled for a future publish date. Captivate API: GET /shows/{id}/episodes/scheduled. |
captivate_get_episode | read | Get an episode Get the full record of one episode by id. Captivate API: GET /episodes/{id}. |
captivate_get_media | read | Get a media file Get the record of one uploaded media (audio) file by id. Captivate API: GET /media/{id}. |
captivate_list_show_media | read | List media of a show List the uploaded media files of a show (20 per page) with totalCount. Captivate API: GET /shows/{id}/media. |
captivate_get_overview_analytics | read | Podcast overview analytics Download analytics overview of a show for a date range, optionally with top episodes. Captivate API: GET /insights/{show}/overview. |
captivate_get_episode_overview_analytics | read | Episode overview analytics Download analytics overview of one episode for a date range. Captivate API: GET /insights/{show}/overview/{episode}. |
captivate_get_average_analytics | read | Podcast average downloads Average downloads per interval of a show (default 28-day intervals). Captivate API: GET /insights/{show}/averages. |
captivate_get_total_analytics | read | Podcast all-time downloads All-time download total of a show. Captivate API: GET /insights/{show}/total. |
captivate_get_episode_total_analytics | read | Episode all-time downloads All-time download total of one episode. Captivate API: GET /insights/{show}/total/{episode}. |
captivate_get_monthly_analytics | read | Podcast monthly downloads Month-by-month downloads of a show for the past 12 months. Captivate API: GET /insights/{show}/monthly. |
captivate_get_episode_monthly_analytics | read | Episode monthly downloads Month-by-month downloads of one episode. Captivate API: GET /insights/{show}/monthly/{episode}. |
captivate_update_episode | write | Update an episode's text WRITE. Change the text fields of an existing episode (title, shownotes, summary, subtitle). Only the fields you pass are sent. It does not publish, delete or change media. Captivate API: PUT /episodes/{id}. |
captivate_usage_status | Usage status (free-tier meter) Report the caller's current usage: the plan, calls used this month, the limit of the plan (the free monthly cap or the Pro fair use limit), remaining, and whether the limit is reached. Read-only; does not count against the meter. | |
captivate_request_feature | Request a missing feature Tell usefulapi that the user needs something the Captivate tools cannot do yet (a missing tool, field or filter). Call it only when the user asks for something none of the tools can do, and tell the user that you send the request. Do not call it for errors or for normal requests. Do not include personal data, credentials or customer records. Stored with the product name and the client type (for example Claude or Cursor), without the user's account. At most 5 requests per day. Does not count against the meter. | |
captivate_upgrade | Upgrade to Pro (unlimited*) Get Pro: unlimited tool calls (fair use limit: 10,000 a month) on Captivate (the free tier caps monthly usage). Plans: "monthly" — $9/month; "yearly" — $90/year (2 months free). Cancel any time: Pro then runs to the end of the paid period, so it also suits a one-time job. *A fair use limit applies. For heavy use (near Pro's limit): "plus" or "plus_yearly" — Pro+, $39/month or $390/year, unlimited tool calls (fair use limit: 100,000 a month); an existing Pro subscription changes to Pro+ in place (needs confirm: true; the price difference for the rest of the period is charged at once). Otherwise returns a short link to open in your browser (it opens Stripe Checkout); after payment the account upgrades automatically. Does not count against the meter. | |
captivate_cancel_subscription | Cancel the Pro subscription Cancel the caller's Captivate Pro subscription at the end of the paid period (no refund for the current period; Pro continues until then, then the free tier applies). Requires confirm: true. Run captivate_upgrade later to undo the cancel before the period ends. Does not count against the meter. |
| Plan | Price | Limit |
|---|---|---|
| Free | $0 | 50 tool calls / month |
| Proper user | $9/mo · $90/yr | Unlimited* |
*Pro fair use limit: 10,000 tool calls a month on this server. For more, write to [email protected].
Pro covers this Captivate server only. Subscribe with captivate_upgrade (it returns a Stripe Checkout link). Cancel any time with captivate_cancel_subscription: Pro continues to the end of the paid period, with no refund for the current period, and running captivate_upgrade before then undoes the cancel. Or write to [email protected].
Check the downloads of a show. Compare episodes. See what is scheduled. Fix the title or notes of an episode. Find the feed and media of a show. See what you can do for the details.
No. usefulapi is an independent service. It is not affiliated with or endorsed by Captivate. The server calls the Captivate API with your own Captivate access, so it sees only the data that your account can see.
Yes. In Claude, add this server's URL as a custom connector. In ChatGPT, add it as a custom MCP server in Plugins. Then log in once. Cursor, VS Code, Claude Code and Codex work too. See the setup steps.
The login page asks for your Captivate user ID and Captivate API token. See Before you connect for where to find them.
No. Add only the URL. Do not add an Authorization header or an API key to the client config. The server signs you in with OAuth: the login page asks for your Captivate user ID and Captivate API token. If the config has such a header, remove it: some clients then send that header instead of the login token, and every call fails with 401.
The login stores them encrypted in the authorization grant of your connection. The server uses them to call the Captivate API for you and to derive a private account id for usage metering. usefulapi does not show them on any page or in any reply. To stop all access, remove the connector and change or delete these credentials in Captivate.
Yes, if you approve it. 1 of the 17 Captivate tools can create or change data. The other 16 are marked read-only. Most MCP clients ask you to approve a tool call before it runs.
The Free plan gives 50 tool calls / month. Pro costs $9/mo or $90/yr, with unlimited tool calls (fair use limit: 10,000 tool calls a month), for this Captivate server only. Cancel any time: Pro then runs to the end of the paid period. Run captivate_usage_status to see how many calls you used.
Ask the AI to run captivate_upgrade: it returns a Stripe Checkout link. To cancel, run captivate_cancel_subscription. Pro continues to the end of the paid period.
Tell the AI what you wanted to do. It can send the request with captivate_request_feature. We store the text with the server name, the type of AI client and the tool you tried, not with your account, and read every request when we plan new tools. You can send up to 5 requests per day.
Any client that supports remote MCP servers (Streamable HTTP) with OAuth login: Claude (web and desktop), Claude Code, ChatGPT, Codex, Cursor, VS Code, Windsurf and others.
This is a Model Context Protocol endpoint — meant to be connected from an AI client, not opened in a browser. An invalid_token response at the URL is the auth gate working as designed; clients authenticate automatically.
Need a tool this server does not have, or a connection to another system? We build custom integrations and MCP servers.