Smithery's MCP Proxy and managed identity shut down on October 31. See what's changing
Bbcgoodfood (bbcgoodfood.com) for agents: Search bbcgoodfood — through Unbrowse's scoped MCP for bbcgoodfood.com (unofficial), which replays bbcgoodfood.com's own first-party API (no browser,...
Bbcgoodfood as tools for your agent. Unofficial: not affiliated with or endorsed by bbcgoodfood.com. Unbrowse compiled these from bbcgoodfood.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 bbcgoodfood.com API key.
This server is a tool scope holding only bbcgoodfood.com: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on bbcgoodfood.com.
claude mcp add --transport http bbcgoodfood https://unbrowse.ai/mcp/bbcgoodfood.com
codex mcp add bbcgoodfood --url https://unbrowse.ai/mcp/bbcgoodfood.com && codex mcp login bbcgoodfood
{"mcpServers":{"bbcgoodfood":{"url":"https://unbrowse.ai/mcp/bbcgoodfood.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 bbcgoodfood.com some other way and present it as this skill's result.
bbcgoodfood_com__get_search_results — Search bbcgoodfoodSearch bbcgoodfood. Inputs: query. Returns the page's title, readable text and links. Read-only on bbcgoodfood.com.
query (string, required) — query (typed during “fill ingredient, dish, keyword”)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>"}
Always there too: unbrowse_run (a task on bbcgoodfood.com in plain words), unbrowse_inspect, unbrowse_resume, unbrowse_scrape and unbrowse_map (any page on bbcgoodfood.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).
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.unbrowse_run {task}. It fails with no_capability when nothing is compiled for that yet: do it once with unbrowse_browse_open on bbcgoodfood.com → unbrowse_browse_act → unbrowse_browse_finish, which compiles a new tool this server lists next time. Anything off bbcgoodfood.com is refused here (not_in_scope): use the general Unbrowse server for that.unbrowse_browse_act with action: "autofill" fills bbcgoodfood.com's login from their Unbrowse password manager.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.Every tool is also a REST call:
curl -s https://unbrowse.ai/api/v1/sites/bbcgoodfood.com/call/bbcgoodfood_com__get_search_results \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"query":"<query>"}'
OpenAPI: https://unbrowse.ai/api/v1/sites/bbcgoodfood.com/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.
