browser_install

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

SERVERCowork Bench SOURCE0717376/cowork_bench

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/cowork-bench/browser-install.md

WHAT IT DOES

What browser_install does on Cowork Bench

AI agents invoke browser_install to trigger actions in Cowork Bench. 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.

RISK

Why browser_install is rated High

This tool installs browser software onto the host system. Installation of software is an external operation with system-level side effects (modifying the filesystem, registry, etc.), which fits the Execute category. It is not purely destructive, financial, or a simple read/write operation. Misuse could result in unwanted software being installed, hence medium severity.

From the tool's definition 'Install the browser specified in the config' — installs software on the system

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_install safely

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

browser_install Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_install": {
      "limits": [
        {
          "counter": "browser_install_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 Cowork Bench, apply this rule, and every browser_install call is checked against it from then on.

FAQ

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 Cowork Bench 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 Cowork Bench 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 Cowork Bench. 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 Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Cowork Bench, and thousands of servers like it.

This server

All 433 Cowork Bench 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 →