connect_to_browser

THE RISK

High Risk

Why connect_to_browser needs a policy

Connecting to a running browser establishes a control channel that enables subsequent execution of arbitrary browser actions (JavaScript, clicks, form fills, etc.). This is an execution-level operation that opens the door to broad automation capabilities with high blast radius if misused by an AI agent.

From the tool's definition 'Подключиться к уже открытому Яндекс Браузеру' (Connect to an already open Yandex Browser) — establishes a live browser session enabling full automation control

Documented attack patterns abuse exactly the kind of access connect_to_browser gives an agent:

POLICY

How to control connect_to_browser

PolicyLayer is an MCP gateway — it sits between your AI agents and Yandex Browser MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for connect_to_browser:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "connect_to_browser": {
      "limits": [
        {
          "counter": "connect_to_browser_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

connect_to_browser stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Yandex Browser MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Yandex Browser MCP Server tools

Execute execute_test Выполнить тест в указанной вкладке: выбрать ответы и отправить Execute navigate Перейти по URL в указанной вкладке Execute wait_for_element Ждать появления элемента Execute evaluate Выполнить JavaScript код в указанной вкладке Execute hover Навести курсор на элемент Execute click Кликнуть по элементу в указанной вкладке Execute key_press Нажать клавишу или комбинацию клавиш Execute scroll Прокрутить страницу или к элементу

All 18 Yandex Browser MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Yandex Browser MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about connect_to_browser

What does the connect_to_browser tool do? +

Подключиться к уже открытому Яндекс Браузеру. It is categorised as a Execute tool in the Yandex Browser MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on connect_to_browser? +

Register the Yandex Browser MCP Server MCP server in PolicyLayer and add a rule for connect_to_browser: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yandex Browser MCP Server. Nothing to install.

What risk level is connect_to_browser? +

connect_to_browser is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit connect_to_browser? +

Yes. Add a rate_limit block to the connect_to_browser rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block connect_to_browser completely? +

Set action: deny in the PolicyLayer policy for connect_to_browser. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides connect_to_browser? +

connect_to_browser is provided by the Yandex Browser MCP Server MCP server (t1trit/yandex-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Yandex Browser MCP Server tool call.

Start from Yandex Browser MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →