Afrinic as tools for your agent. Unofficial: not affiliated with or endorsed by afrinic.net. Unbrowse compiled these from afrinic.net'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 afrinic.net API key.
Connect the afrinic.net MCP
This server is a tool scope holding only afrinic.net: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on afrinic.net.
claude mcp add --transport http afrinic https://unbrowse.ai/mcp/afrinic.net
codex mcp add afrinic --url https://unbrowse.ai/mcp/afrinic.net && codex mcp login afrinic
{"mcpServers":{"afrinic":{"url":"https://unbrowse.ai/mcp/afrinic.net"}}}
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 afrinic.net some other way and present it as this skill's result.
Tools
rdap_afrinic_net__get_ip_196_1_0_0 — Query AFRINIC RDAP for an IP address
Query AFRINIC RDAP for an IP address. Inputs: rdap. Returns rdapConformance, notices, handle, lang, links, events, status, port43. Read-only on rdap.afrinic.net.
rdap(string, required)
{"rdap":"<rdap>"}
afrinic_net__read_page — Read a page on afrinic.net
Read any page on afrinic.net — a path such as /news/2026/some-story, or a full afrinic.net 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 afrinic.net.
path(string, required) — A page on afrinic.net: a path like /about, or a full URL on afrinic.net
{"path":"/"}
Always there too: unbrowse.run (a task on afrinic.net in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on afrinic.net), 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 afrinic.net →unbrowse.browse.act→unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off afrinic.net 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 afrinic.net'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/rdap.afrinic.net/call/rdap_afrinic_net__get_ip_196_1_0_0 \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"rdap":"<rdap>"}'
OpenAPI: https://unbrowse.ai/api/v1/sites/rdap.afrinic.net/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.