Navigate to a specific URL and return the page's HTML content.
AI agents invoke browse_to to trigger actions in MCP Web Browser Server. 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 drives a headless browser to navigate to an arbitrary URL, which is an external operation that triggers network requests, potentially executes JavaScript on the target page, and may cause side effects depending on the URL visited. It is more than a passive read — it actively operates a browser engine. Severity is medium because misuse could lead to SSRF, internal network probing, or loading malicious pages.
From the tool's definition Navigate to a specific URL and return the page's HTML content
Documented attack patterns abuse exactly the kind of access browse_to gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Web Browser Server, and nothing reaches the server without passing your rules. This is the rule we recommend for browse_to:
{
"version": "1",
"default": "deny",
"tools": {
"browse_to": {
"limits": [
{
"counter": "browse_to_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}browse_to 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.
Navigate to a specific URL and return the page's HTML content. It is categorised as a Execute tool in the MCP Web Browser Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Web Browser Server MCP server in PolicyLayer and add a rule for browse_to: 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 MCP Web Browser Server. Nothing to install.
browse_to 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 browse_to 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 browse_to. 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.
browse_to is provided by the MCP Web Browser Server MCP server (random-robbie/mcp-web-browser). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Web Browser Server, 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.
6 MCP Web Browser Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.