Raspberrypi as tools for your agent. Unofficial: not affiliated with or endorsed by raspberrypi.org. Unbrowse compiled these from raspberrypi.org'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 raspberrypi.org API key.
Connect the raspberrypi.org MCP
This server is a tool scope holding only raspberrypi.org: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on raspberrypi.org.
claude mcp add --transport http raspberrypi https://unbrowse.ai/mcp/raspberrypi.org
codex mcp add raspberrypi --url https://unbrowse.ai/mcp/raspberrypi.org && codex mcp login raspberrypi
{"mcpServers":{"raspberrypi":{"url":"https://unbrowse.ai/mcp/raspberrypi.org"}}}
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 raspberrypi.org some other way and present it as this skill's result.
Tools
projects_raspberrypi_org__get_projects_search — Search projects on Raspberry Pi projects site
Search projects on Raspberry Pi projects site. Inputs: query. Returns projects. Read-only on projects.raspberrypi.org.
query(string, required) — query (typed during “fill Search”)
{"query":"<query>"}
raspberrypi_org__read_page — Read a page on raspberrypi.org
Read any page on raspberrypi.org — a path such as /news/2026/some-story, or a full raspberrypi.org 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 raspberrypi.org.
path(string, required) — A page on raspberrypi.org: a path like /about, or a full URL on raspberrypi.org
{"path":"/"}
Always there too: unbrowse.run (a task on raspberrypi.org in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on raspberrypi.org), 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
- 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.
- Read
status.succeededcarries the verifiedresult.input_requiredis not a failure: answer the open fields withunbrowse.resume {runId, answers}on the same run. - No tool fits:
unbrowse.run {task}. It fails withno_capabilitywhen nothing is compiled for that yet: do it once withunbrowse.browse.openon raspberrypi.org →unbrowse.browse.act→unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off raspberrypi.org is refused here (not_in_scope): use the general Unbrowse server for that. - Signing in: never ask the user for a password.
unbrowse.browse.actwithaction: "autofill"fills raspberrypi.org's login from their Unbrowse password manager. - Report only what a
succeededresult says.outcome_unknownmeans 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/projects.raspberrypi.org/call/projects_raspberrypi_org__get_projects_search \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"query":"<query>"}'
OpenAPI: https://unbrowse.ai/api/v1/sites/projects.raspberrypi.org/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.