# Browseai — how to use (mcp.ai)

Connect your Browseai account and use 11 tools for web scraping straight from your AI agent. Connect with your own API key. Browse.ai allows you to turn any website into an API using its advanced web automation and data extraction tools, enabling easy monitoring and data retrieval from websites.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_browseai?ms=1787291340000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `browseai_bulk_run_tasks`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/browseai`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/browseai/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/browseai/bulk/run/tasks` — This action allows users to bulk run up to 1,000 tasks per API call using a specified robot. For larger datasets, submit multiple bulk runs sequentially (up to 500,000 tasks total). It provides a POST
  - body: { title: string, robot_id: string, input_parameters: object[] }
- `POST https://api.mcp.ai/api/browseai/create/monitor` — Creates a new monitor for a Browse AI robot to automatically track website changes over time. A monitor runs a robot on a recurring schedule and can notify you when the captured data (screenshots or t
  - body: { name: string, robot_id: string, schedule?: string, input_parameters?: object, notify_on_text_change?: boolean, notify_on_screenshot_change?: boolean, screenshot_notification_threshold?: integer }
- `POST https://api.mcp.ai/api/browseai/create/webhook` — This tool creates a new webhook for a Browse AI robot. Webhooks are HTTP callbacks that Browse AI sends to your server immediately when specific events occur, eliminating the need for polling. It is u
  - body: { url: string, events?: string[], robot_id: string, is_active?: boolean, description?: string }
- `POST https://api.mcp.ai/api/browseai/delete/monitor` — This tool allows users to delete a specific monitor from their Browse AI account. It uses the DELETE method and requires a valid monitor_id.
  - body: { monitor_id: string }
- `POST https://api.mcp.ai/api/browseai/delete/task` — This tool allows you to delete a specific task in BrowseAI by its task ID. It is used for cleaning up completed or failed tasks, managing resources, and maintaining your task list.
  - body: { task_id: string, robot_id: string }
- `POST https://api.mcp.ai/api/browseai/get/robot/tasks` — Retrieves a paginated list of all tasks (execution runs) for a specific Browse AI robot. Each task represents one execution of the robot, which includes its current status, execution timestamps, input
  - body: { limit?: integer, offset?: integer, robot_id: string }
- `POST https://api.mcp.ai/api/browseai/get/robots` — Retrieves a list of all robots (automated web tasks) under your Browse AI account. A robot is an automated browser task that can be trained to perform web operations such as: - Opening webpages and na
- `POST https://api.mcp.ai/api/browseai/get/system/status` — Tool to check the operational status of Browse AI infrastructure, including the tasks queue condition. Use when you need to verify if Browse AI services are operational before running robots or tasks.
- `POST https://api.mcp.ai/api/browseai/get/task/details` — Retrieves detailed information about a specific Browse AI task by robot ID and task ID. This tool returns comprehensive task details including execution status, captured data, screenshots, input param
  - body: { task_id: string, robot_id: string }
- `POST https://api.mcp.ai/api/browseai/list/robot/webhooks` — Tool to retrieve all webhooks configured for a specific Browse AI robot. Use when you need to view, audit, or manage webhook configurations for a robot. Returns webhook details including URL, event ty
  - body: { robot_id: string }
- `POST https://api.mcp.ai/api/browseai/run/robot` — Triggers the execution of a Browse.ai robot to extract data from websites. This action starts a new robot task that will scrape/extract data according to the robot's pre-configured settings. The robot
  - body: { robot_id: string, input_parameters?: object }

## Example prompts
- "What can I do in Browseai?"
- "Show me a summary of my Browseai account"

## More
- Page: https://mcp.ai/browseai
- Agent spec (llms.txt): https://mcp.ai/browseai/llms.txt
- Postman collection: https://mcp.ai/browseai/postman.json