Smithery is now a part of Arcade.dev! Read more in our announcement here
Aepd (aepd.es) for agents: Search AEPD publications and resolutions; Search AEPD frequently asked questions; Read a page on aepd.es — through Unbrowse's scoped MCP for aepd.es (unofficial), which...
Aepd as tools for your agent. Unofficial: not affiliated with or endorsed by aepd.es. Unbrowse compiled these from aepd.es'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 aepd.es API key.
This server is a tool scope holding only aepd.es: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on aepd.es.
claude mcp add --transport http aepd-es https://unbrowse.ai/mcp/aepd.es
codex mcp add aepd-es --url https://unbrowse.ai/mcp/aepd.es && codex mcp login aepd-es
{"mcpServers":{"aepd-es":{"url":"https://unbrowse.ai/mcp/aepd.es"}}}
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 aepd.es some other way and present it as this skill's result.
aepd_es__get_buscador — Search AEPD publications and resolutionsSearch AEPD publications and resolutions. Inputs: query. Returns the page's title, readable text and links. Read-only on aepd.es.
query (string, required) — query (typed during “fill Buscador general”){"query":"<query>"}
aepd_es__get_preguntas_frecuentes_buscador — Search AEPD frequently asked questionsSearch AEPD frequently asked questions. Inputs: query. Returns the page's title, readable text and links. Read-only on aepd.es.
query (string, required) — query (typed during “fill Formulario de búsqueda de preguntas frecuentes”){"query":"<query>"}
aepd_es__read_page — Read a page on aepd.esRead any page on aepd.es — a path such as /news/2026/some-story, or a full aepd.es 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 aepd.es.
path (string, required) — A page on aepd.es: a path like /about, or a full URL on aepd.es{"path":"/"}
Always there too: unbrowse.run (a task on aepd.es in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on aepd.es), 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 aepd.es → unbrowse.browse.act → unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off aepd.es is refused here (not_in_scope): use the general Unbrowse server for that.unbrowse.browse.act with action: "autofill" fills aepd.es'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/aepd.es/call/aepd_es__get_buscador \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"query":"<query>"}'
OpenAPI: https://unbrowse.ai/api/v1/sites/aepd.es/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.
