Unbrowse for F5 (f5.com)

F5 as tools for your agent. Unofficial: not affiliated with or endorsed by f5.com. Unbrowse compiled these from f5.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 f5.com API key.

Connect the f5.com MCP

This server is a tool scope holding only f5.com: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on f5.com.

claude mcp add --transport http f5 https://unbrowse.ai/mcp/f5.com
codex mcp add f5 --url https://unbrowse.ai/mcp/f5.com && codex mcp login f5

{"mcpServers":{"f5":{"url":"https://unbrowse.ai/mcp/f5.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 f5.com some other way and present it as this skill's result.

Tools

f5_com__get_search — Search f5.com

Read search on www.f5.com on Hybrid Multicloud App Security & Delivery for the AI Era | F5 (www.f5.com). Use for requests like “search www.f5.com for security”; “search www.f5.com for application”; “search www.f5.com for application — Search f5.com for application”. Learned from 2 browser traces; chains get_search. Inputs: query e.g. "security". Returns the page's title, readable text and links. Read-only on f5.com.

• query (string, required) — query (typed during “fill Search all F5 sites”), e.g. "security", "application"

{"query":"security"}

Always there too: unbrowse.run (a task on f5.com in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on f5.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 f5.com → unbrowse.browse.act → unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off f5.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 f5.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/f5.com/call/f5_com__get_search \
  -H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
  -d '{"query":"security"}'

OpenAPI: https://unbrowse.ai/api/v1/sites/f5.com/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.