SuperAPI AI Directory
Partner中文AI newsFavorites
Skillsprimevideo

primevideo

Design & creation

View repository

Updated 10-16 07:16

About this skill

Unbrowse for Primevideo (primevideo.com)

Primevideo as tools for your agent. Unofficial: not affiliated with or endorsed by primevideo.com. Unbrowse compiled these from primevideo.com's own requests: each call replays the site's first-party API server-side and returns a verified result. No scraping of rendered pages, no browser on your side, no primevideo.com API key.

Connect the primevideo.com MCP

This server is a tool scope holding only primevideo.com: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on primevideo.com.

claude mcp add --transport http primevideo https://unbrowse.ai/mcp/primevideo.com
codex mcp add primevideo --url https://unbrowse.ai/mcp/primevideo.com && codex mcp login primevideo

{"mcpServers":{"primevideo":{"url":"https://unbrowse.ai/mcp/primevideo.com"}}}

The first connect signs in to Unbrowse with OAuth (free tier, only verified results count). For scripts, send Authorization: Bearer $UNBROWSE_API_KEY (key from https://unbrowse.ai/app/keys; keep it in a secret manager, never in config you commit).

If none of the tools below are in this session's tool list, the server is not connected or not signed in: say so and stop. Do not fetch primevideo.com some other way and present it as this skill's result.

Tools

primevideo_com__get_search — Search amazonvideo.com

Read search on www.primevideo.com on Welcome to Prime Video (www.primevideo.com). Use for requests like “search www.primevideo.com for trial”; “search www.primevideo.com for trial — Search amazonvideo.com for trial”. Learned from 1 browser trace; chains get_offers_nonprimehomepage → get_search_suggestions → get_search. Inputs: query e.g. "trial"; type (optional) e.g. "CONTENT_CARDS". Returns the page's title, readable text and links. Read-only on primevideo.com.

  • query (string, required) — query (typed during “fill Search”), e.g. "trial"
  • type (string) — type, e.g. "CONTENT_CARDS", "WORDS"
{"query":"start","type":"CONTENT_CARDS"}

primevideo_com__read_page — Read a page on primevideo.com

Read any page on primevideo.com — a path such as /news/2026/some-story, or a full primevideo.com URL — and get its title, readable text and links. One first-party HTTP request, no browser. Follow a returned link by passing its href back as the path. Inputs: path e.g. "/". Returns the page's title, readable text and links. Read-only on primevideo.com.

  • path (string, required) — A page on primevideo.com: a path like /about, or a full URL on primevideo.com
{"path":"/"}

Always there too: unbrowse.run (a task on primevideo.com in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on primevideo.com), and the recorded cloud browser unbrowse.browse.open → unbrowse.browse.act → unbrowse.browse.finish. Hosts that reject dotted names show them with _ (unbrowse_run).

How to call

  1. Pick the tool whose title matches the job and pass its inputs. Leave the site's recorded parameters out unless the user asked for something they control.
  2. Read status. succeeded carries the verified result. input_required is not a failure: answer the open fields with unbrowse.resume {runId, answers} on the same run.
  3. No tool fits: unbrowse.run {task}. It fails with no_capability when nothing is compiled for that yet: do it once with unbrowse.browse.open on primevideo.com → unbrowse.browse.act → unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off primevideo.com is refused here (not_in_scope): use the general Unbrowse server for that.
  4. Signing in: never ask the user for a password. unbrowse.browse.act with action: "autofill" fills primevideo.com's login from their Unbrowse password manager.
  5. Report only what a succeeded result says. outcome_unknown means a change may have happened: check before retrying. Posting, buying, sending or deleting needs the user's go-ahead.

Without MCP

Every tool is also a REST call:

curl -s https://unbrowse.ai/api/v1/sites/primevideo.com/call/primevideo_com__get_search \
  -H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
  -d '{"query":"start","type":"CONTENT_CARDS"}'

OpenAPI: https://unbrowse.ai/api/v1/sites/primevideo.com/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.