TinyFish

Only use when the user asks for one Monitor. Requires monitor_id from list_monitors or create_monitor.

get_monitor

Only use when you need to find a run_id for a recently created automation, usually after run_web_automation timed out before returning one. Lists automation runs with optional filtering by status and pagination. Filter by status=RUNNING to find active runs.

list_runs

Lists Browser Context Profiles, including which one is the default. signed_in_sites are sites where a TinyFish setup saw the user sign in, or the user said they signed in when saving, and whose cookies are still saved; a sign-in may have expired since its claimed_at. For a site that needs sign-in, prefer a profile whose signed_in_sites includes that site and pass its exact profile_id. An entry covers its subdomains (google.com covers docs.google.com), and some sign-ins are recorded under the provider's site: microsoftonline.com covers office.com, microsoft365.com and sharepoint.com, and x.com covers twitter.com. An entry does not show which account or tenant. A profile that only matches by name is not confirmed signed in: ask the user whether it is before running on it, and call start_profile_setup_session for it only if they say so.

list_profiles

Only use when the user asks which Monitors they have. Returns each Monitor id, type, target, schedule, and status.

list_monitors

Only use when the user asks to pause a Monitor. Stops its schedule until resume_monitor.

pause_monitor

Only use when the user asks to resume a paused Monitor and start its schedule again.

resume_monitor

Metered web automation is available through your wallet — use it for clicking, forms, login, or dynamic pages. Use for one user-directed website task that requires browser interaction: navigating a specific site or page, clicking, filling forms, logging in, checking page state, or completing a workflow requested by the user. Opens one live browser session the user can see in the widget. Returns immediately with a runId. Then call wait_for_run with that runId until status is terminal, and present the results. Do NOT call get_run or list_runs to check progress. Do not use for broad crawling, bulk URL processing, or unspecified third-party access. For authenticated or recurring workflows, pass use_profile=true; pass profile_id for a specific Browser Context Profile; pair with use_vault=true to repair stale sessions. WARNING: If errors or times out, run is STILL EXECUTING. DO NOT call again. If a run returns an insufficient-credits or subscription message, that is expected and recoverable: relay the upgrade or top-up link to the user and ask whether they want to upgrade or top up to continue. Do NOT silently fall back to a weaker tool or tell the user you cannot browse the web.

run_web_automation

Only use when the user asks to check a Monitor immediately. Runs once and returns that result.

run_monitor

Saves cookies and browser storage from a setup session onto the profile, then closes the browser. The inline card and setup_url page save for the user, so do not call this for those flows. Pass signed_in_sites with the sites the user says they signed into; never add sites they did not mention. Follow any next_step it returns. Omit capability.

save_profile_setup_session

Searches the public web and returns compact, structured results. Appropriate when the user requests current public information, source-backed research, or help finding a relevant page. When a user-requested task needs details from a result, its URL can be passed to fetch_content. Optionally provide purpose — a short statement of why you are searching and what the results are for — so results can be ranked against the underlying intent; it is not required and may be omitted. Supports geo-targeting (location), language filtering, recency_minutes for past-N-minute freshness, and after_date / before_date for YYYY-MM-DD date windows. Do not combine recency_minutes with after_date or before_date. Use domain_type to scope the search: "web" (default), "news" for news articles, or "research_paper" for academic papers. For domain_type=research_paper, use pub_year_min / pub_year_max instead to scope by publication year (inclusive) — after_date, before_date, and recency_minutes are not supported for research_paper. Use include_domains / exclude_domains (comma-separated domain lists) to restrict or remove specific domains from results. Use page (0-indexed, 0-10) to paginate through results.

search

Returns setup_url for signing in to an EXISTING Browser Context Profile. Give the user that page to sign in and save their browser state. Use create_profile for a new profile. Optional url opens the site first. Never ask for a password in chat.

start_profile_setup_session

Wait for a run started by run_web_automation. Blocks up to 50 seconds, then returns the current status. While status is pending or running, call it again with the same run_id. When status is completed, failed, or cancelled, the result or error is included — present it to the user. If this tool errors, call it again with the same run_id; do not start a new run. Do not use get_run to poll instead.

wait_for_run