Anchor Browser MCP connector for AI agents

Anchor Browser MCP tools for AI agents

CALL ANY TOOL

12 tools covering anchor.

anchorbrowsermcp_anchor_click

Perform a click on an element in the cloud browser page. use

Perform a click on an element in the cloud browser page. use `element` to provide a human-readable description of the target (e.g. 'submit button') and `ref` to supply the exact element reference obtained from a prior `anchor_snapshot` accessibility snapshot. optionally set `doubleclick` to true to perform a double-click instead.

Parameters

Name

Type

Required

Description

element

string

Required

Human-readable element description used to obtain permission to interact with the element

ref

string

Required

Exact target element reference from the page snapshot

doubleClick

boolean

Optional

Whether to perform a double click instead of a single click

anchorbrowsermcp_anchor_close

Close the current browser page and end the active cloud brow

anchorbrowsermcp_anchor_console_messages

Returns all console messages captured since the current page

anchorbrowsermcp_anchor_drag

Perform a drag-and-drop operation between two elements in th

anchorbrowsermcp_anchor_file_upload

Upload one or more files to the cloud browser page via a fil

anchorbrowsermcp_anchor_generate_playwright_code

Generate a playwright test script for a given scenario descr

anchorbrowsermcp_anchor_get_body_html

Get the html content of the body element from the current pa

anchorbrowsermcp_anchor_handle_dialog

Accept or dismiss a browser dialog (alert, confirm, or promp

anchorbrowsermcp_anchor_hover

Hover the mouse cursor over an element in the cloud browser

anchorbrowsermcp_anchor_navigate

Navigate the cloud browser to a specified url, loading the p

anchorbrowsermcp_anchor_navigate_back

Go back to the previous page in the browser history, equival

anchorbrowsermcp_anchor_navigate_forward

Go forward to the next page in the browser history, equivale

Build your Agent

Same auth pattern across every framework.

from langchain_mcp_adapters.client import MultiServerMCPClient
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="anchorbrowsermcp")

mcp = MultiServerMCPClient({
    "anchorbrowsermcp": {
        "url": "https://mcp.scalekit.com/anchorbrowsermcp",
        "headers": {"Authorization": "Bearer " + token}
    }
})
tools = await mcp.get_tools()

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "anchorbrowsermcp" });

const openai = new OpenAI();
// Connect to MCP at https://mcp.scalekit.com/anchorbrowsermcp
// Pass: Authorization: Bearer + token

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const client = new ScalekitClient({ envUrl, clientId, clientSecret });
const token = await client.agent.getToken({ userId: "user_id", connector: "anchorbrowsermcp" });

const anthropic = new Anthropic();
// Connect to MCP at https://mcp.scalekit.com/anchorbrowsermcp
// Pass: Authorization: Bearer + token

from google.adk.agents import LlmAgent
from scalekit import ScalekitClient

client = ScalekitClient(env_url=ENV_URL, client_id=CLIENT_ID, client_secret=SECRET)
token = client.agent.get_token(user_id="user_id", connector="anchorbrowsermcp")
# Connect to MCP at https://mcp.scalekit.com/anchorbrowsermcp
# Pass: Authorization: Bearer + token

Try these prompts

Paste any prompt into your agent to get started.

Get started

Copy the prompt

Copied

Pause the automation until a specified text appears on the page, a specified text disappears from the page, or a given n?

Copy the prompt

Copied

Type text into an editable element in the cloud browser page?

Advanced

Copy the prompt

Copied

Take a screenshot of the current browser page or a specific element?

Copy the prompt

Copied

Switch the active browser tab to the tab at the given zero-based index?

SEE HOW AUTH WORKS

User authorises once. Every agent call after uses their token with scope enforcement.

Authorize

Your user connects

Anchor Browser MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Anchor Browser MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Anchor Browser MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Anchor Browser MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other connectors.

No items found.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

Other connector libraries treat auth as a demo afterthought.

01.

Shared tokens break per-user analytics

A shared token looks fine in a demo. In production every call looks like a service account. Scalekit resolves the real user credential.

// shared token
 audit → bot_service_account

 // scalekit
 audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

One connector today. Ten tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Anchor Browser as the user or as a shared key?
As the user. Each workspace member authorizes once and Scalekit resolves their credential at request time. Audit logs attribute every action to that user, not a shared service account.

Where is the Anchor Browser OAuth token stored?
In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Tokens never appear in prompts, logs, or LLM context.

Can I limit what the agent is allowed to do in Anchor Browser?
Yes. Pass a tool name filter to listScopedTools so the AI agent only sees the subset you authorize. Pre-API-call scope checks block out-of-policy actions before the request reaches Anchor Browser.

What happens when a user revokes Anchor Browser access?
The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Are browser sessions isolated per user?
Yes. Each cloud browser session, click, and extraction runs under the authorizing user's Anchor Browser account. Sessions, cookies, and captured data never cross user boundaries.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit