browser_open

SERVERYaver SOURCEyaver-cli

High RISK CLASS

Category Execute

Parameters 60 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-kivanccakmak-yaver/browser-open.md

WHAT IT DOES

What browser_open does on Yaver

AI agents invoke browser_open to trigger actions in Yaver. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`record`	boolean	—	Record this session to an MP4 video of everything the agent does in it (headless-safe). The response returns clip_id + clip_url; the clip finalizes on browser_c
`headful`	boolean	—	Show browser window visibly (default: false, headless)
`profile`	string	—	F2 persistent profile (name or absolute path). Reuses a user-data-dir so cookies + Cloudflare clearance PERSIST across runs. Pass the SAME profile name to brows
`proxy_url`	string	—	Egress proxy for this session's vantage, e.g. http://host:8080 or socks5://host:1080. Omit for machine-native egress. Only use proxies/peers the user owns or is
`session_id`	string	—	Custom session ID (auto-generated if omitted)
`record_seconds`	number	—	Optional safety cap (seconds) for recording; defaults to a 600s cap. Recording normally stops at browser_close, not this cap.

Parameters from the server's own tool schema.

RISK

Why browser_open is rated High

This tool executes a real browser process on the developer's machine, with persistent state (cookies, auth). Misuse could enable unauthorized browsing, credential harvesting via session persistence, or traffic exfiltration through proxy routing. It triggers external operations whose effects depend on arguments, placing it firmly in Execute. The proxy routing capability elevates severity to high.

From the tool's definition 'Open a new Chrome browser session on the dev machine' and 'Pass proxy_url to egress through a chosen vantage' — launches external browser process and enables network traffic routing through arbitrary proxies

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_open safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_open, this is the rule to start with:

browser_open Rate-limited

browser_open 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every browser_open call is checked against it from then on.

FAQ

Questions about browser_open

What does the browser_open tool do? +

Open a new Chrome browser session on the dev machine. Returns a session_id to use in subsequent browser_* calls. Sessions persist across tool calls — cookies, auth state, and current URL survive between steps. Pass proxy_url to egress through a chosen vantage (a proxy or peer the user is entitled to use); the source then sees that egress IP, not this machine's. It is categorised as a Execute tool in the Yaver MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does browser_open accept? +

browser_open accepts 6 parameters: record, headful, profile, proxy_url, session_id, record_seconds. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on browser_open? +

Register the Yaver MCP server in PolicyLayer and add a rule for browser_open: 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 Yaver. Nothing to install.

What risk level is browser_open? +

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

Can I rate-limit browser_open? +

Yes. Add a rate_limit block to the browser_open 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 browser_open completely? +

Set action: deny in the PolicyLayer policy for browser_open. 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 browser_open? +

browser_open is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Yaver, and thousands of servers like it.

This server

All 645 Yaver tools → High-risk tools on this server →

Across the catalogue

browser_click on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →