Install Playwright Chromium browser binary. Call this if you get an error about the browser not being installed.
AI agents invoke browser_install to trigger actions in Fetch MCP. 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.
This tool installs software (a browser binary) onto the host system, which is an external operation with side effects beyond simple data retrieval or writing. It modifies the system state by downloading and installing a binary, making it an Execute category action. Misuse could lead to installation of unexpected software or version conflicts, hence medium severity.
From the tool's definition Install Playwright Chromium browser binary
Documented attack patterns abuse exactly the kind of access browser_install gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fetch MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for browser_install:
{
"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.
Free to start. No card required.
Install Playwright Chromium browser binary. Call this if you get an error about the browser not being installed. It is categorised as a Execute tool in the Fetch MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Fetch 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 Fetch MCP. Nothing to install.
browser_install is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
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.
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.
browser_install is provided by the Fetch MCP server (jae-jae/fetcher-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Fetch MCP, 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.
3 Fetch MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.