AI agents invoke open_urls to trigger actions in MCP System Bridge. 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 triggers an external operation (launching URLs in the browser), whose effects depend on the URLs provided. A malicious agent could open phishing pages, trigger drive-by downloads, cause unwanted network requests, or abuse browser-based OAuth flows.
From the tool's definition "Open a list of URLs in the default browser"
Documented attack patterns abuse exactly the kind of access open_urls gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP System Bridge, and nothing reaches the server without passing your rules. This is the rule we recommend for open_urls:
{
"version": "1",
"default": "deny",
"tools": {
"open_urls": {
"limits": [
{
"counter": "open_urls_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}open_urls 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.
Open a list of URLs in the default browser. It is categorised as a Execute tool in the MCP System Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP System Bridge MCP server in PolicyLayer and add a rule for open_urls: 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 System Bridge. Nothing to install.
open_urls 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 open_urls 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 open_urls. 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.
open_urls is provided by the MCP System Bridge MCP server (leynier/mcp-sys-bridge). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP System Bridge, 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.
4 MCP System Bridge tools catalogued and risk-classified — across an index of 43,000+ MCP servers.