Anchor browser

Anchor browser MCP integration

Reads pages that expose no API, drives portal and form work to completion, runs versioned browser tasks by name, and reuses saved login profiles.

Connect Anchor browserSee all integrations

64actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

  • Perform web task

    Lyro executes autonomous browser tasks like form filling, navigation, and data extraction in real-time. Complex workflows complete without human intervention.

  • Create task

    Lyro defines a reusable browser automation workflow with specific steps and logic. Your team triggers it repeatedly for consistent results across campaigns.

  • Get task execution result

    Lyro retrieves the output, status, and extracted data from a completed automation. You see exactly what the task accomplished and any errors that occurred.

See all 64 actions

How businesses use Anchor browser + Lyro

Each card is one request a support team gets, and the Anchor browser actions Lyro runs to close it.

  • Read a page that has no API behind it

    Lyro fetches the rendered content of a page as HTML or markdown, captures a screenshot when the layout is the point, and lists the pages open in the session, so an answer comes from the live site.

    Get Webpage ContentScreenshot WebpageGet Session Pages

  • Finish a job on a site that has no integration

    Lyro hands the objective to an autonomous web task, or steps through it directly by navigating to the page and typing into the form, so a supplier portal with no API still gets updated.

    Perform Web TaskNavigate to URLType Text

  • Run a browser task that is versioned like code

    Lyro creates a reusable task, deploys it as a new auto-incremented version, and runs it by name so every execution uses the latest published version rather than a copy somebody pasted.

    Create TaskDeploy TaskRun Task by Name

  • Start signed in and close down cleanly

    Lyro saves cookies and session state from an authenticated session as a profile, starts later sessions from it instead of logging in again, and ends every open session when the work is done.

    Create ProfileStart Browser SessionEnd All Sessions

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Anchor browser actions it has and picks the ones a request needs.

  1. 01

    Connect Anchor browser

    Authorize the Anchor browser account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.

  2. 02

    Tell your agent what you need

    Describe the job the way you would hand it to a teammate. Lyro maps it to the Anchor browser actions that close it and chains as many as the request needs.

  3. 03

    Watch it work

    The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.

    Get started free
Anchor browser · Lyro

Everything else about Anchor browser

Setup, permissions, and the limits of what Lyro can do inside Anchor browser.

  • Create Profile stores the cookies, local storage, and session state from an active session, and Update Profile refreshes that store from a later one. Start Browser Session can then open with the profile attached, so credentials are not re-entered on every run. Delete Profile clears the stored state when an account is retired.

Every action available in Anchor browser

All 64 actions your agent can call on Anchor browser, straight from the live MCP connection.

  • Click mouse

    Perform a mouse click at specified coordinates within a browser session.

  • Copy selected text

    Copy currently selected text in a browser session to the clipboard.

  • Create integration

    Create a new integration with a third-party service like 1Password.

  • Create or update task draft

    Create or update the draft version of a task.

  • Create profile

    Creates a new browser profile from an active session.

  • Create task

    Create a new task or update an existing task with the same name.

  • Delete extension

    Delete a browser extension and remove it from storage.

  • Delete integration

    Delete an existing integration and remove its stored credentials.

  • Delete profile

    Delete a browser profile by ID.

  • Delete task

    Soft delete a task and all its versions.

  • Delete task version

    Soft delete a specific version of a task.

  • Deploy task

    Deploy a task by creating a new version with auto-incremented version number.

  • Double click mouse

    Perform a double click at specified coordinates in a browser session.

  • Drag and drop

    Perform a drag and drop operation from start coordinates to end coordinates within a browser session.

  • End all sessions

    Terminate all active browser sessions at once.

  • End browser session

    End a specific browser session by ID.

  • Get batch session status

    Retrieve detailed status information for a specific batch including progress and errors.

  • Get browser session

    Retrieve detailed information about a specific browser session.

  • Get clipboard content

    Retrieve the current content of the clipboard from a browser session.

  • Get latest task version

    Retrieve the latest version of a task including the full base64 encoded code content.

  • Get profile (v2)

    Retrieve details of a specific profile by its name.

  • Get session pages

    Retrieve all pages associated with a specific browser session.

  • Get task draft

    Retrieve the draft version of a task, including the full Base64 encoded code content.

  • Get task execution result

    Retrieve a single task execution result by its ID.

  • Get task metadata

    Retrieve task metadata without downloading the full task code.

  • Get task version

    Retrieve a specific version of a task, including the full code content.

  • Get webpage content

    Retrieve rendered content of a webpage in HTML or Markdown format.

  • List agent resources

    List all agent resources (files) uploaded to a browser session.

  • List extensions

    Retrieves all browser extensions uploaded by the authenticated user.

  • List integrations

    Retrieve all integrations for the authenticated team.

The tools Anchor browser sits next to

Same connection, same setup. Pick the next one your team already uses.

Browse every integration

Ready to connect Anchor browser?

Authorize the account and your agent has all 64 actions from the first conversation.

Connect Anchor browserTalk to sales
Support agent working at a laptop next to the Lyro mascot