Anchor Browser is a developer platform that enables AI agents to interact with the web through browser automation, transforming complex web interactions into simple API endpoints.
Anchor Browser is a developer platform that enables AI agents to interact with the web through browser automation, transforming complex web interactions into simple API endpoints. On Nagent, Anchor Browser is exposed as a fully-configurable ai agents integration that any agent can call — 64 actions, and API key authentication. No code is required to wire Anchor Browser into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Anchor Browser to automate the kinds of tasks ai agents teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Anchor Browser into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Anchor Browser, with input parameters and output schema. Drop these into any step of an agent built in Helix.
ANCHOR_BROWSER_CLICK_MOUSETool to perform a mouse click at specified coordinates within a browser session. Use when you need to interact with page elements by clicking at specific x/y positions. The click is executed in the context of the specified browser session.
Input parameters
The x-coordinate (horizontal position) on the page where the mouse click should occur
The y-coordinate (vertical position) on the page where the mouse click should occur
The mouse button to click. Valid values are 'left', 'right', or 'middle'. Defaults to 'left' if not specified
The ID of the browser session where the click should be performed
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_COPY_SELECTED_TEXTTool to copy currently selected text in a browser session to the clipboard. Use when you need to extract text that the user or automation has selected in the browser.
Input parameters
Unique identifier for the browser session from which to copy selected text.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_CREATE_INTEGRATIONTool to create a new integration with a third-party service like 1Password. Use when you need to set up an integration for managing credentials or accessing external services. The integration will be available immediately after creation for use in browser sessions and profiles.
Input parameters
Name for the integration. Must be at least 1 character long.
The type of integration to create. Currently only '1PASSWORD' is supported.
Credentials required to authenticate with the third-party service.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_CREATE_OR_UPDATE_TASK_DRAFTTool to create or update the draft version of a task. Draft versions are used for development and testing before publishing. Use when you need to save task code changes without creating a published version.
Input parameters
The code content for the draft version. Must be base64 encoded.
The unique identifier of the task to create or update the draft for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_CREATE_PROFILECreates a new browser profile from an active session. A profile stores cookies, local storage, and cache data. The session must be running when this is called; profile data is persisted once the session terminates. Use profiles to maintain persistent browser state across multiple sessions.
Input parameters
Unique identifier name for the profile. Must not conflict with existing profile names.
The source of the profile data. Currently only 'session' is supported.
The ID of an active browser session to create the profile from. The session must be running; profile data (cookies, local storage, cache) will be persisted when the session terminates.
Optional description providing context about the profile's purpose.
When true, reserves a dedicated sticky IP for this profile. Any browser session started with this profile will automatically use this reserved IP address.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_CREATE_TASKTool to create a new task or update an existing task with the same name. Tasks are reusable TypeScript code snippets that execute in browser sessions. Use when you need to define repeatable automation workflows that can be invoked across multiple sessions.
Input parameters
Base64 encoded task implementation code. The code will be executed in the browser session context.
Task identifier. Must contain only letters, numbers, hyphens, and underscores (1-255 characters).
Programming language for the task. Currently only 'typescript' is supported.
Human-readable description of what the task does. Maximum 1000 characters.
Complete browser configuration for task execution.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DELETE_EXTENSIONTool to delete a browser extension and remove it from storage. Use after confirming the extension exists.
Input parameters
The unique identifier (UUID) of the extension to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DELETE_INTEGRATIONTool to delete an existing integration and remove its stored credentials. Use after confirming the integration ID exists.
Input parameters
The ID of the integration to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DELETE_PROFILETool to delete a browser profile by ID. Use after confirming the profile exists.
Input parameters
The unique name (ID) of the browser profile to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DELETE_TASKTool to soft delete a task and all its versions. Use after confirming the task exists.
Input parameters
The unique identifier (UUID) of the task to delete.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DELETE_TASK_VERSIONTool to soft delete a specific version of a task. The version will no longer be accessible but data is preserved for recovery. Use when you need to remove a specific task version.
Input parameters
The unique identifier (UUID) of the task containing the version to delete.
The version number to delete. Can be a numeric version or 'latest'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DEPLOY_TASKTool to deploy a task by creating a new version with auto-incremented version number. Use when you need to publish task changes and make them available for execution.
Input parameters
Base64 encoded task code. The code will be deployed as a new version.
The ID of the task to deploy (UUID format).
Programming language for the task code. Must be 'typescript'.
Optional version description (max 1000 characters). Helps document changes in this deployment.
Browser settings for task execution including proxy, timeout, viewport, and feature toggles.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DOUBLE_CLICK_MOUSETool to perform a double click at specified coordinates in a browser session. Use when you need to trigger double-click events on UI elements or specific page locations.
Input parameters
X coordinate for the double click position in pixels
Y coordinate for the double click position in pixels
The ID of the browser session where the double click should be performed
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_DRAG_AND_DROPTool to perform a drag and drop operation from start coordinates to end coordinates within a browser session. Use when you need to simulate dragging UI elements or files in automated workflows.
Input parameters
End X coordinate in pixels where the element will be dropped.
End Y coordinate in pixels where the element will be dropped.
Start X coordinate in pixels for the drag operation.
Start Y coordinate in pixels for the drag operation.
The ID of the browser session where the drag and drop operation will be performed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_END_ALL_SESSIONSTool to terminate all active browser sessions at once. Use when you need to immediately close every browser session for the authenticated user, such as during cleanup operations or security concerns.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_END_BROWSER_SESSIONTool to end a specific browser session by ID. Use after confirming the session ID you want to terminate.
Input parameters
Unique identifier for the browser session to end.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_BATCH_SESSION_STATUSTool to retrieve detailed status information for a specific batch including progress and errors. Use when you need to check the status of a batch session creation request.
Input parameters
The unique identifier of the batch
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_BROWSER_SESSIONTool to retrieve detailed information about a specific browser session. Use when you need to check the status, configuration, or execution details of a browser session.
Input parameters
The unique identifier of the session to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_CLIPBOARD_CONTENTTool to retrieve the current content of the clipboard from a browser session. Use when you need to read clipboard data from an active session.
Input parameters
The ID of the browser session to retrieve clipboard content from.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_LATEST_TASK_VERSIONTool to retrieve the latest version of a task including the full base64 encoded code content. Use when you need to access the most recent task implementation.
Input parameters
The unique identifier (UUID) of the task to retrieve the latest version for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_PROFILE2Tool to retrieve details of a specific profile by its name. Use when you need to fetch information about a particular browser profile.
Input parameters
The name of the profile to retrieve.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_SESSION_PAGESTool to retrieve all pages associated with a specific browser session. Use when you need to list all open tabs or pages in an active or completed session.
Input parameters
The ID of the session to retrieve pages for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_TASK_DRAFTTool to retrieve the draft version of a task, including the full Base64 encoded code content. Use when you need to access the current draft of a task that hasn't been published yet.
Input parameters
The unique identifier of the task to retrieve the draft version for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_TASK_EXECUTION_RESULTTool to retrieve a single task execution result by its ID. Use when you need to check the status, output, or error details of a specific task execution.
Input parameters
The unique identifier of the task (UUID format)
The unique identifier of the execution result (UUID format)
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_TASK_METADATATool to retrieve task metadata without downloading the full task code. Use when you need task information such as status, creation time, or language without the code content.
Input parameters
The unique identifier of the task to retrieve metadata for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_TASK_VERSIONTool to retrieve a specific version of a task, including the full code content. Use when you need to access the complete task code for a particular version (draft, latest, or specific version number).
Input parameters
The unique identifier of the task (UUID format).
The version identifier to retrieve. Use 'draft' for the draft version, 'latest' for the most recent deployed version, or a specific version number.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_GET_WEBPAGE_CONTENTTool to retrieve rendered content of a webpage in HTML or Markdown format. Use when you need to fetch a page’s full content, optionally within an existing browser session.
Input parameters
The URL of the webpage to fetch content from. If omitted when using a session, fetches the current page in that session.
Milliseconds to wait for dynamic content to load before extracting the page content.
Output format for the returned content: 'html' for raw HTML or 'markdown' for formatted text.
Whether to create a new page/tab in the browser session for this request.
Browser session identifier to execute within an existing session context. If not provided, a new temporary session is created for this request.
Index of the browser page/tab to fetch content from. Supersedes 'new_page' if provided.
If True, return partial content if the page loading exceeds the 20-second timeout instead of failing.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_AGENT_RESOURCESList all agent resources (files) uploaded to a browser session. Returns metadata for each file including name, size, file type, and last modified timestamp. Requires an active running session - use START_BROWSER_SESSION first. Files can be uploaded using UPLOAD_FILE action.
Input parameters
The unique identifier (UUID) of an active browser session. Obtain this from the START_BROWSER_SESSION action response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_EXTENSIONSRetrieves all browser extensions uploaded by the authenticated user. Use this to view available extensions that can be attached to browser sessions for automation tasks.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_INTEGRATIONSTool to retrieve all integrations for the authenticated team. Use when you need to view available integrations that can be used with browser sessions.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_PROFILESTool to fetch all stored browser profiles. Use when you need an overview of all profiles available to the authenticated user (e.g., after creating or deleting profiles).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_SESSION_DOWNLOADSTool to retrieve metadata of files downloaded during a browser session. Use after confirming the session ID.
Input parameters
The unique identifier of the browser session to retrieve downloads for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_SESSION_RECORDINGSTool to list all recordings for a specific browser session. Use after confirming the session ID.
Input parameters
The unique identifier (UUID) of the browser session to retrieve recordings for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_SESSIONSTool to list all browser sessions. Use when you need to retrieve both active and inactive sessions.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_TASK_EXECUTIONSTool to retrieve execution history for a specific task with filtering and pagination support. Use when you need to view past execution results, monitor task success rates, or debug failed executions.
Input parameters
Page number for pagination. Must be a positive integer. Default is '1'.
Number of executions to return per page. Must be a positive integer between 1 and 100. Default is '10'.
Execution status values for filtering task executions.
The unique identifier of the task to retrieve executions for (UUID format).
Filter executions by task version. Can be 'draft', 'latest', or a specific version number.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_TASKSTool to retrieve a paginated list of all tasks for the authenticated team. Use when you need to view available tasks with their latest version information and metadata.
Input parameters
Page number for pagination. Must be a positive integer. Default is '1'.
Number of tasks to return per page. Must be a positive integer between 1 and 100. Default is '10'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_LIST_TASK_VERSIONSTool to retrieve all versions of a specific task, including draft and published versions. Use when you need to view the version history of a task or select a specific version for deployment or execution.
Input parameters
The unique identifier (UUID) of the task to retrieve versions for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_MOVE_MOUSETool to move the mouse cursor to specified coordinates within a browser session. Use when you need to simulate mouse movement at the OS level.
Input parameters
X coordinate to move the mouse cursor to.
Y coordinate to move the mouse cursor to.
The ID of the browser session where the mouse should be moved.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_NAVIGATE_TO_URLTool to navigate a browser session to a specified URL. Use when you need to direct an existing session to a new webpage.
Input parameters
The URL to navigate to. Must be a valid HTTP or HTTPS URL.
The ID of the browser session to navigate.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PASTE_TEXTTool to paste text at the current cursor position in a browser session. Use when you need to insert text into an active form field or text area.
Input parameters
Text to paste at the current cursor position in the browser session.
The ID of the browser session where text should be pasted. Must be a valid active session ID returned from starting a browser session.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PAUSE_AGENTTool to pause the AI agent for a specific browser session. Use when you need to temporarily halt autonomous agent execution while keeping the session active.
Input parameters
The ID of the browser session for which to pause the AI agent.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PAUSE_SESSION_RECORDINGTool to pause the video recording for a specific browser session. Use when you need to temporarily stop recording without ending the session.
Input parameters
The unique identifier of the browser session for which to pause recording.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PERFORM_KEYBOARD_SHORTCUTTool to perform a keyboard shortcut using specified keys in a browser session. Use when you need to simulate keyboard input like copy (Control+C), paste (Control+V), or any other key combination.
Input parameters
Array of keys to press simultaneously. Examples: \['Control', 'c'\] for copy, \['Control', 'v'\] for paste, \['Alt', 'Tab'\] for window switch.
Time to hold the keys down in milliseconds. If not specified, uses default key press duration.
Unique identifier for the browser session where the keyboard shortcut will be performed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PERFORM_WEB_TASKTool to perform autonomous web tasks using AI agents. Use when you need to automate complex browser interactions like form filling, data extraction, or multi-step workflows.
Input parameters
The URL of the webpage where the task should be performed. If omitted when using a session, uses the current page in that session.
The AI agent type to use for task completion. Each agent has different capabilities and performance characteristics.
Run the task asynchronously and return immediately with a workflow ID. When false (default), waits for task completion before returning.
Specific model identifier to use for task completion. Model availability depends on the selected provider.
The task description that the AI agent should complete autonomously on the webpage. Be specific about the desired outcome.
The AI provider to use for task execution. If omitted, uses the default provider for the selected agent.
Maximum number of steps the agent can take to complete the task. Defaults to 200. Higher values allow for more complex multi-step workflows.
Browser session identifier to execute the task within an existing session context. If not provided, a new temporary session is created.
JSON Schema defining the expected structure of the task output. The agent will format its response according to this schema.
Secure credential handling via environment variables. Keys are variable names, values are sensitive data that should not be logged.
Enable element detection to improve interaction accuracy with UI elements. Useful for complex forms and dynamic interfaces.
Visually highlight UI elements during task execution. Useful for debugging and understanding agent behavior.
Allow human input during task execution. When enabled, the agent can request user assistance for ambiguous situations.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PRESS_MOUSE_BUTTONTool to perform a mouse button down action at specified coordinates within a browser session. Use when you need to simulate pressing and holding a mouse button at a specific screen position.
Input parameters
The x-coordinate (horizontal position) in pixels where the mouse button should be pressed down.
The y-coordinate (vertical position) in pixels where the mouse button should be pressed down.
The mouse button to press down. Defaults to 'left' if not specified.
The ID of the browser session in which to perform the mouse down action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_PUBLISH_TASK_VERSIONTool to publish a specific version of a task. Creates a new version if it doesn't exist, or updates an existing version's metadata. Use when you need to make a specific task version available for execution. Cannot publish to 'draft' versions.
Input parameters
Base64-encoded task code to publish. The code will be executed in the browser session context.
The ID of the task (UUID format).
Programming language of the task code. Supported values: 'javascript' or 'typescript'.
Optional task version description (maximum 1000 characters). Helps document what changed in this version.
The version number to publish. Must be a numeric string (e.g., '1', '2'). Cannot be 'draft'.
Optional browser configuration including initial URL, tags, recording settings, proxy, timeout, and live view options.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_RELEASE_MOUSE_BUTTONTool to release a mouse button at specified coordinates within a browser session. Use when automating mouse interactions that require button release events, such as completing drag operations or simulating natural mouse behavior.
Input parameters
X-coordinate (horizontal position in pixels) where the mouse button up action should occur.
Y-coordinate (vertical position in pixels) where the mouse button up action should occur.
Enumeration of mouse button types.
Unique identifier for the browser session where the mouse up action will be performed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_RESUME_AGENTTool to resume the AI agent for a specific browser session. Use when you need to restart agent execution after it has been paused or stopped.
Input parameters
Unique identifier for the browser session where the agent should be resumed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_RESUME_SESSION_RECORDINGTool to resume video recording for a specific browser session. Use when recording was previously paused and needs to be restarted.
Input parameters
The unique identifier (UUID) of the browser session to resume recording for.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_RUN_TASKTool to execute a task in a browser session with a specific or latest version. Use when you need to run an existing task with optional session reuse and configuration overrides.
Input parameters
Whether to run the task asynchronously. If true, returns immediately with task status; if false (default), waits for task completion
Environment variables for task execution. All keys must start with 'ANCHOR_' prefix
Task identifier (UUID format)
Version to run: 'draft' for the current draft version, 'latest' for the latest published version, or a specific version number
Optional existing browser session ID to use for task execution. If not provided, a new session will be created
Whether to cleanup browser sessions after task execution. Defaults to true if not specified
Session-related configurations to override default browser settings.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_RUN_TASK_BY_NAMETool to execute a task by its name, always using the latest version. Use when you need to run a predefined browser automation task by referencing its name.
Input parameters
Environment variables for task execution. All keys must start with 'ANCHOR_' prefix
The name of the task to execute. This will use the latest version of the task
Optional existing session ID to use for task execution
Optional task-specific session ID for tracking
Browser configuration override for task execution.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_SCREENSHOT_WEBPAGETool to take a screenshot of a specified webpage within a session. Use when you need a visual PNG snapshot of a live page. Example: "Capture a 1280×720 screenshot of https://example.com".
Input parameters
The fully qualified URL of the webpage to capture. Must include the protocol (https:// or http://).
Time in milliseconds to wait after page load before capturing. Useful for pages with JavaScript animations or delayed content loading. Defaults to 0.
Browser viewport width in pixels. Determines the width of the rendered page before capture. Defaults to 1280.
Browser viewport height in pixels. Determines the visible area height (unless capture_full_height is true). Defaults to 720.
Existing browser session ID to use for the screenshot. If provided, the screenshot is taken within that session's browser context. If omitted, a new temporary session is created.
Output image quality as a percentage (1-100). Higher values produce larger, sharper images. 100 means no compression. Defaults to 80.
Pre-signed S3 URL where the screenshot should be uploaded directly. If provided, the image is uploaded to S3 instead of being returned in the response. Useful for large screenshots or when storing for later use.
If true, scrolls through the entire page before capture to trigger lazy-loaded images and dynamic content. Set to true for pages with infinite scroll or lazy loading.
If true, captures the entire document height (full page) instead of just the visible viewport. Useful for capturing long scrolling pages.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_SCROLL_SESSIONTool to perform a scroll action at specified coordinates within a browser session. Use when you need to scroll to specific positions or simulate user scrolling behavior. Example: "Scroll down 100 pixels from position (100, 100) in session sess_123".
Input parameters
The horizontal coordinate (in pixels) where the scroll action starts.
The vertical coordinate (in pixels) where the scroll action starts.
Number of intermediate steps to divide the scroll into. Higher values create smoother scrolling animations.
If true, uses OS-level scroll events instead of browser-level scroll. Useful for simulating more realistic human scrolling behavior.
The horizontal scroll distance in pixels. Positive values scroll right, negative values scroll left.
The vertical scroll distance in pixels. Positive values scroll down, negative values scroll up.
The ID of the browser session where the scroll action will be performed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_SET_CLIPBOARD_CONTENTTool to set the content of the clipboard in a browser session. Use when you need to programmatically copy text to the clipboard for automated workflows.
Input parameters
Text to set in the clipboard.
The ID of the browser session.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_SIGNAL_EVENTTool to signal a specific event to be received by other processes or sessions. Use when you need real-time coordination across browser sessions after verifying session is active.
Input parameters
The JSON payload to send with the event.
The name of the event to signal.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_START_BROWSER_SESSIONTool to start a new browser session with optional customizations. Use when you need to programmatically allocate an isolated browser instance with recording, proxy, live view, and feature toggles.
Input parameters
Browser-level configurations including profile, viewport, and feature toggles (adblock, captcha solver, etc.)
Session-level configurations including recording, proxy, timeouts, and live view settings
Previously configured identities for authenticated sessions (Beta feature)
Array of integrations to load in the browser session (e.g., 1Password). Integrations must be previously created using the Integrations API
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_TAKE_SCREENSHOTTool to take a screenshot of the current browser session and return it as an image. Use when you need a visual snapshot of an active browser session.
Input parameters
The ID of the browser session to capture a screenshot from.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_TYPE_TEXTTool to type specified text with optional delay between keystrokes. Use when you need to input text into a browser session, such as filling forms or entering search queries.
Input parameters
The text to type into the browser session.
Delay between keystrokes in milliseconds. If not specified, types at normal speed.
The ID of the browser session where text should be typed.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_UPDATE_PROFILEUpdates an existing browser profile with data from an active session. The profile stores cookies, local storage, and cache from the session. Requires an active (running) browser session - the session_id must reference a session that has not been terminated.
Input parameters
The unique name (ID) of the browser profile to update. Must be an existing profile.
The source of the profile data. Currently only 'session' is supported.
The UUID of an active browser session to update the profile from. The session must be currently running.
A new description for the profile. If not provided, the description remains unchanged.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_UPDATE_TASK_METADATAUpdates task metadata (name and description). This does not affect the task code or versions. Use when you need to update task information without modifying the implementation.
Input parameters
New name for the task. If not provided, the name remains unchanged.
The ID of the task to update. Must be an existing task.
New description for the task. If not provided, the description remains unchanged.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_UPLOAD_EXTENSIONTool to upload a new browser extension as a ZIP file for use in browser sessions. Use when you need to add custom extensions that can be attached to automation sessions. The ZIP file must contain a valid extension manifest (manifest.json). Extensions are scoped to the authenticated user and can be listed or attached to sessions later.
Input parameters
ZIP file containing the browser extension. Required if file_content_base64 is not provided.
User-friendly name for the extension. Must be between 1-255 characters.
Filename for the extension ZIP when using file_content_base64 (e.g., 'extension.zip'). Required when using file_content_base64.
Base64-encoded ZIP file content. If provided, this is used directly instead of fetching from S3 storage. Useful for direct file uploads or testing. Required if file is not provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_UPLOAD_FILETool to upload a file to a browser session as an agent resource. Use after starting or referencing a session when you need to provide file inputs (single files or ZIP archives) for web forms or AI-driven tasks. Supports direct base64-encoded content or S3 key references from other actions.
Input parameters
File information including name and mimetype.
The ID of the browser session to upload the file to. Must be a valid active session ID returned from starting a browser session.
Base64-encoded file content. If provided, this is used directly instead of the file reference. Useful for direct file uploads or testing.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_UPLOAD_FILES_TO_SESSIONTool to upload files directly to a browser session for use with web forms and file inputs. Use when you need to provide file inputs to web forms during automated browser sessions.
Input parameters
File to upload to the browser session.
The ID of the browser session to upload the file to. Must be a valid active session ID returned from starting a browser session.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
ANCHOR_BROWSER_WAIT_FOR_EVENTBlocks execution until a specific named event is signaled or the timeout expires. Used for cross-session coordination, MFA handling, and workflow synchronization. The event must first be signaled using the Signal Event action. Returns the data payload that was sent with the signal. Events are user-scoped.
Input parameters
Maximum time in milliseconds to wait for the event before timing out. Defaults to 60000ms (60 seconds). Maximum allowed is 300000ms (5 minutes).
The unique name of the event to wait for. Must match the event_name used by the signaling process (via Signal Event action). Event names are user-scoped and case-sensitive.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 32 agents privately built on Nagent that already use Anchor Browser.
Build on Nagent
Connect Anchor Browser to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Anchor Browser, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Anchor Browser is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Anchor Browser is connected, you configure its 64 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Anchor Browser steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Anchor Browser event fires, the agent kicks off automatically.
Every Anchor Browser action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Anchor Browser ships with 64 pre-built ai agents actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Anchor Browser together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Anchor Browser-based workflows tailored to your business.