SuperAPI AI Directory

v2ex

General & other

View repository

Updated 10-16 07:16

About this skill

Unbrowse for V2ex (v2ex.com)

V2ex as tools for your agent. Unofficial: not affiliated with or endorsed by v2ex.com. Unbrowse compiled these from v2ex.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 v2ex.com API key.

Connect the v2ex.com MCP

This server is a tool scope holding only v2ex.com: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on v2ex.com.

claude mcp add --transport http v2ex https://unbrowse.ai/mcp/v2ex.com
codex mcp add v2ex --url https://unbrowse.ai/mcp/v2ex.com && codex mcp login v2ex
{"mcpServers":{"v2ex":{"url":"https://unbrowse.ai/mcp/v2ex.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 v2ex.com some other way and present it as this skill's result.

Tools

v2ex_com__render_page — Search v2ex.com

Search v2ex.com and read the results page (/go/apple). The site builds its results in the browser, so each run renders the page (Unbrowse's own browser, then a hosted renderer when the site blocks it) instead of calling an API: seconds, not milliseconds. Use for requests like “search v2ex.com for apple — Search v2ex.com for apple”. Inputs: query e.g. "apple". Returns the page's title, readable text and links. Read-only on v2ex.com.

  • query (string, required) — query — what to search for on v2ex.com
{"query":"muse"}

v2ex_com__read_page — Read a page on v2ex.com

Read any page on v2ex.com — a path such as /news/2026/some-story, or a full v2ex.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 v2ex.com.

  • path (string, required) — A page on v2ex.com: a path like /about, or a full URL on v2ex.com
{"path":"/"}

Always there too: unbrowse.run (a task on v2ex.com in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on v2ex.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 v2ex.com → unbrowse.browse.act → unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off v2ex.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 v2ex.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/v2ex.com/call/v2ex_com__render_page \
  -H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
  -d '{"query":"muse"}'

OpenAPI: https://unbrowse.ai/api/v1/sites/v2ex.com/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.