Tools

Get Bulk Run

Retrieve the status and progress of a bulk run. Returns the current state, counts of successful and failed tasks, and completion timestamp. Use this to monitor the progress of large-scale extraction operations.

List Tasks

List tasks for a given robot with optional filtering by status, date range, and bulk run. Supports pagination. Returns task IDs, statuses, extracted data, and metadata for each task.

List Webhooks

List all webhooks configured for a specific robot. Returns the webhook IDs, destination URLs, and event types.

Delete Webhook

Remove a webhook from a robot. The webhook will stop receiving event notifications immediately.

Create Webhook

Register a new webhook on a robot that fires when a specific event occurs. Supported event types: `taskFinished`, `taskFinishedSuccessfully`, `taskFinishedWithError`, `taskCapturedDataChanged`, `tableExportFinishedSuccessfully`.

Update Robot Cookies

Update the cookies associated with a robot. This is useful for maintaining authenticated sessions on target websites that require login. Provide the cookies as an array of cookie objects.

Get Task

Retrieve the status and results of a specific task. When the task has completed successfully, the response includes extracted data in `capturedTexts` and any captured screenshots. Use this to check task progress or fetch scraped data after running a robot.

Create Bulk Run

Submit a bulk run to process many pages in a single operation. Provide a list of input parameter sets (typically URLs) and a descriptive title. This is the recommended approach for large-scale data extraction instead of creating individual tasks.

Run Task

Execute a web scraping robot on-demand by providing its ID and input parameters (typically an `originUrl`). The task runs asynchronously — the response includes the task ID and its initial status. Use **Get Task** to poll for results once the task completes.

Get Robot

Retrieve detailed information about a specific Browse AI robot by its ID. Returns the robot's name, creation date, and the input parameters it accepts including parameter names, types, and whether they are required.

List Robots

Retrieve all configured web scraping robots in your Browse AI account. Returns each robot's ID, name, creation date, and the input parameters it accepts. Use this to discover available robots before running tasks.

Get System Status

Check whether Browse AI’s task queue is operational or under maintenance before diagnosing delayed robot tasks.

Download Task Data

Download a task’s captured text, tables, and screenshot metadata as JSON. Uses the provider’s temporary data download for results larger than 100 KB. Discover task IDs with list_tasks.

List Bulk Runs

Discover a robot’s bulk runs with status, task counts, and pagination. Call list_robots for robot IDs, then get_bulk_run for task-level results.

Update Monitor

Change a monitor’s schedule, input parameters, notifications, or name; pause it with status paused or resume with status active. Discover IDs with list_robots and list_monitors.

List Monitors

List a robot’s scheduled monitors, their IDs, schedules, notification settings, and pause reasons. Call list_robots first to discover robot IDs.

Delete Monitor

Permanently delete a scheduled monitor. Discover the monitor ID with list_monitors.

Get Monitor

Retrieve a scheduled monitor’s current status, schedule, parameter overrides, notifications, and pause details. Discover IDs with list_robots and list_monitors.

Create Monitor

Create a scheduled monitor with its own input parameters and change notification settings. Call list_robots and get_robot to discover a robot and its inputs.