Navigate a specific Arc tab, or the active tab when explicitly omitted.
AI agents use arc_open_url to create or update resources in Arc Browser MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Arc Browser MCP environment.
Opening/navigating a URL modifies the state of a browser tab by changing its location. This is a reversible write action (the tab can be navigated back or to a different URL). It does not execute arbitrary code, delete data, or move money, though it could be misused to navigate to malicious URLs.
From the tool's definition Navigate a specific Arc tab, or the active tab when explicitly omitted.
Attacks that exploit this kind of access
Navigate a specific Arc tab, or the active tab when explicitly omitted. It is categorised as a Write tool in the Arc Browser MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Arc Browser MCP server in PolicyLayer and add a rule for arc_open_url: 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 Arc Browser MCP. Nothing to install.
arc_open_url is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the arc_open_url 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 arc_open_url. 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.
arc_open_url is provided by the Arc Browser MCP server (jasoncronje/arc-browser-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →