SuperAPI AI Directory

caniuse

General & other

View repository

Updated 10-16 07:16

About this skill

Unbrowse for Caniuse (caniuse.com)

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

Connect the caniuse.com MCP

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

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

Tools

caniuse_com__get_process_query — Search caniuse

Search caniuse. Inputs: query. Returns featureIds. Read-only on caniuse.com.

  • query (string, required) — query (typed during “fill Search”)
  • select (array) — Keep only these parts of the result: dots walk keys, [] maps over a list, a final {a,b} keeps several keys (e.g. "results[].{title,url}"). Unmatched paths come back in selectMissing.
{"query":"<query>"}

caniuse_com__get_search — Search caniuse.com

Search caniuse.com with its own search (published OpenSearch description) and read the results page as title, text and links. One first-party HTTP request, no browser. Inputs: query. Returns the page's title, readable text and links. Read-only on caniuse.com.

  • query (string, required) — query — what to search for on caniuse.com
  • select (array) — Keep only these parts of the result: dots walk keys, [] maps over a list, a final {a,b} keeps several keys (e.g. "results[].{title,url}"). Unmatched paths come back in selectMissing.
{"query":"features"}

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

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