High Risk →

browser_install

Install the browser specified in the config. Call this if you get an error about the browser not being installed.

How to control browser_install ↓

What browser_install does on Wuying AgentBay

AI agents invoke browser_install to trigger actions in Wuying AgentBay. 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.

High Risk

Why browser_install needs a policy

This tool installs software (a browser) in the cloud execution environment. Installation is an execution-type operation that modifies the system state by deploying a new application. It is not purely destructive, financial, or a simple read/write of data, but it does trigger an external operation (software installation) whose effects depend on the configuration provided.

From the tool's definition Install the browser specified in the config. Call this if you get an error about the browser not being installed.

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

How to control browser_install

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_install": {
      "limits": [
        {
          "counter": "browser_install_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

browser_install 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.

  1. Create a free account and register Wuying AgentBay — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RATE-LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about browser_install

What does the browser_install tool do? +

Install the browser specified in the config. Call this if you get an error about the browser not being installed. It is categorised as a Execute tool in the Wuying AgentBay MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on browser_install? +

Register the Wuying AgentBay MCP server in PolicyLayer and add a rule for browser_install: 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 Wuying AgentBay. Nothing to install.

What risk level is browser_install? +

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

Can I rate-limit browser_install? +

Yes. Add a rate_limit block to the browser_install 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_install completely? +

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

browser_install is provided by the Wuying AgentBay MCP server (michael98671/agentbay). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Wuying AgentBay tool call.

Start from Wuying AgentBay, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

59 Wuying AgentBay tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.