> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to BrowserAct

The BrowserAct connector lets your AI agent act in each user's BrowserAct account. Each user connects their own BrowserAct access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 12 tools.

**Authentication:** Bearer Token
**Categories:** Automation
**Tools:** 12: 8 read, 3 write, 1 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=BROWSERACT)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the BrowserAct connection

   In **AgentKit > Connections**, create a BrowserAct connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'browseract'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize BrowserAct:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'browseract_bots_list',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "browseract"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize BrowserAct:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="browseract_bots_list",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their BrowserAct credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'browseract_bot_get',
  toolInput: {
    bot_id: '<bot_id>',
  },
  connector: 'browseract',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="browseract_bot_get",
    tool_input={
        "bot_id": "<bot_id>",
    },
    connection_name="browseract",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `browseract_bot_get`

Get Bot · Read-only

Get one BrowserAct Bot by ID, including its published input and output schemas.
Returns bot_id, bot_type, name, description, created_at, published_at, input_schema and output_schema (both null when unpublished).
Use this before browseract_bot_run to build an input that matches input_schema. Use browseract_bots_list to find IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bot_id` (`string`, required): Public Bot ID. Get it from browseract_bots_list. Example: bot_8f2c1a7e4d.

Example input: `{"bot_id":"<bot_id>"}`

### `browseract_bots_list`

List Bots · Read-only

List the Bots in your BrowserAct account that have a runnable published version, with optional type and name filters.
Returns items with bot_id, bot_type, name, description and published_at, plus page, limit, total_count and total_pages.
Use this to find a bot_id. Use browseract_bot_get to see one Bot's input_schema before running it.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bot_type` (`string`, optional): Only return Bots of this type. Example: workflow. One of: `workflow`, `agent`.
- `keyword` (`string`, optional): Case-insensitive search on the Bot name, up to 200 characters. Example: amazon.
- `limit` (`integer`, optional): Bots per page, 1 to 100. BrowserAct defaults to 20. Example: 20.
- `page` (`integer`, optional): Page number to retrieve, starting at 1. BrowserAct defaults to 1. Example: 1.

Example input: `{}`

### `browseract_regions_list`

List Proxy Regions · Read-only

List the proxy regions your BrowserAct API key can use for template runs.
Returns each region's code and name.
Use this to pick proxy_region for browseract_template_run.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs: none.

Example input: `{}`

### `browseract_task_get`

Get Task · Read-only

Get the full details of one BrowserAct task, including its output.
Returns status, the accepted input, output, failure details, files, live browser information and step summaries when available.
Use this to read results once a task has finished. Use browseract_task_status_get for lightweight polling.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `task_id` (`string`, required): Task ID returned when the run was created, or from browseract_tasks_list. Example: 1990041234567890123.

Example input: `{"task_id":"<task_id>"}`

### `browseract_task_status_get`

Get Task Status · Read-only

Get only the current status and last update time of one BrowserAct task.
Returns the task status (created, running, pausing, paused, finished, canceled or failed) and its update time.
Use this to poll a run started by browseract_bot_run or browseract_template_run. Use browseract_task_get for the output.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `task_id` (`string`, required): Task ID returned when the run was created, or from browseract_tasks_list. Example: 1990041234567890123.

Example input: `{"task_id":"<task_id>"}`

### `browseract_tasks_list`

List Tasks · Read-only

List Bot runs (tasks) in your BrowserAct account, filtered by status, Bot or creation time, with pagination.
Returns items with task_id, status, bot_id, bot_name and timestamps, plus page, limit, total_count and total_pages.
Use this to browse past runs. Use browseract_task_get for one task's output.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `bot_id` (`string`, optional): Only return tasks created from this Bot ID. Example: bot_8f2c1a7e4d.
- `bot_name` (`string`, optional): Only return tasks whose Bot name contains this text. Example: amazon.
- `created_at_from` (`string`, optional): Only tasks created at or after this time, ISO 8601. Example: 2026-01-01T00:00:00Z.
- `created_at_to` (`string`, optional): Only tasks created at or before this time, ISO 8601. Example: 2026-12-31T23:59:59Z.
- `limit` (`integer`, optional): Tasks per page, 1 to 100. BrowserAct defaults to 20. Example: 20.
- `page` (`integer`, optional): Page number to retrieve, starting at 1. BrowserAct defaults to 1. Example: 1.
- `status` (`string`, optional): Only return tasks with this status. Example: finished. One of: `created`, `running`, `finished`, `canceled`, `pausing`, `paused`, `failed`.

Example input: `{}`

### `browseract_template_get`

Get Official Template · Read-only

Get one official BrowserAct Bot template by ID.
Returns the template's ID, name, description and the input_schema a run must follow.
Use this before browseract_template_run. Use browseract_templates_list to find IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `template_id` (`string`, required): Public official Bot template ID. Get it from browseract_templates_list. Example: tpl_3a9d2e61b0.

Example input: `{"template_id":"<template_id>"}`

### `browseract_templates_list`

List Official Templates · Read-only

List the official Bot templates curated by BrowserAct, with an optional name search.
Returns items with each template's template_id, name and description, plus page, limit, total_count and total_pages.
Use this to find a ready-made scraper. Use browseract_template_get for its input_schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `keyword` (`string`, optional): Case-insensitive search on the template name, up to 200 characters. Example: google maps.
- `limit` (`integer`, optional): Templates per page, 1 to 500. BrowserAct defaults to 10. Example: 10.
- `page` (`integer`, optional): Page number to retrieve, starting at 1. BrowserAct defaults to 1. Example: 1.

Example input: `{}`

### `browseract_bot_run`

Run Bot · Write

Start a run (task) of a published BrowserAct Bot with the given input.
Returns the new task_id and its status, usually created or running; output is not ready yet.
Poll browseract_task_status_get until the task finishes, then read the output with browseract_task_get. Use browseract_template_run for official templates.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `bot_id` (`string`, required): Public Bot ID. Get it from browseract_bots_list. Example: bot_8f2c1a7e4d.
- `input` (`object`, required): Run input object that matches the Bot's input_schema from browseract_bot_get. Send an empty object {} when the Bot takes no inputs. Example: {"keyword": "wireless earbuds", "max_items": 20}
- `callback_url` (`string`, optional): Public HTTP or HTTPS URL that receives a POST with the full task details when the task finishes, fails or is canceled. Maximum 2048 characters; private or local addresses are rejected. Example: https://your-server.com/webhooks/browseract-done.
- `status_change_callback_url` (`string`, optional): Public HTTP or HTTPS URL that receives a POST with the full task details every time the task status changes (running, paused, finished, canceled, failed). Maximum 2048 characters. Example: https://your-server.com/webhooks/browseract-status.

Example input: `{"bot_id":"<bot_id>","input":{"keyword":"wireless earbuds","max_items":20}}`

### `browseract_task_resume`

Resume Task · Write

Ask BrowserAct to resume a paused workflow task. Agent Bot tasks cannot be resumed.
Returns the task's status; it can stay paused for a moment because resuming is asynchronous.
Use this on a task in the paused state. Use browseract_task_cancel to stop a task instead.

Read only: no. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `task_id` (`string`, required): Task ID returned when the run was created, or from browseract_tasks_list. Example: 1990041234567890123.

Example input: `{"task_id":"<task_id>"}`

### `browseract_template_run`

Run Official Template · Write

Start a run (task) of an official BrowserAct Bot template with the given input, optionally through a proxy region.
Returns the new task_id and its status; output is not ready yet.
Poll browseract_task_status_get, then read the output with browseract_task_get. Use browseract_bot_run for your own Bots.

Read only: no. Destructive: no. Idempotent (safe to retry): no.

Inputs:

- `input` (`object`, required): Run input object that matches the template's input_schema from browseract_template_get. Example: {"url": "https://example.com"}
- `template_id` (`string`, required): Public official Bot template ID. Get it from browseract_templates_list. Example: tpl_3a9d2e61b0.
- `callback_url` (`string`, optional): Public HTTP or HTTPS URL that receives a POST with the full task details when the task finishes, fails or is canceled. Maximum 2048 characters; private or local addresses are rejected. Example: https://your-server.com/webhooks/browseract-done.
- `proxy_region` (`string`, optional): Proxy region code to run the browser from. Get valid codes from browseract_regions_list. Example: US.
- `status_change_callback_url` (`string`, optional): Public HTTP or HTTPS URL that receives a POST with the full task details every time the task status changes (running, paused, finished, canceled, failed). Maximum 2048 characters. Example: https://your-server.com/webhooks/browseract-status.

Example input: `{"input":{"url":"https://example.com"},"template_id":"<template_id>"}`

### `browseract_task_cancel`

Cancel Task · Destructive

Cancel a running or paused BrowserAct task. A finished, canceled or failed task cannot be canceled.
Returns the task's new status.
Use this to stop a run you no longer need; a canceled task cannot be resumed.

Read only: no. Destructive: yes. Idempotent (safe to retry): yes.

Inputs:

- `task_id` (`string`, required): Task ID returned when the run was created, or from browseract_tasks_list. Example: 1990041234567890123.
- `biz_code` (`integer`, optional): Optional cancellation code of your own for tracking. BrowserAct uses its default user-cancel code when left out. Example: 1001.

Example input: `{"task_id":"<task_id>"}`

## Related

Other Automation connectors ([all 91](/agentkit/connectors/?category=automation)):

- [Mailchimp](/agentkit/connectors/mailchimp/): Scalekit connector, OAuth, 73 tools
- [Twilio](/agentkit/connectors/twilio/): Scalekit connector, Username and password, 61 tools
- [Stripe](/agentkit/connectors/stripe/): Scalekit connector, Access token, 178 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
