Loads a URL
AI agents invoke navigate to trigger actions in Chrome Devtools. 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.
Navigation is an Execute operation because it triggers external interactions with the web and can have unpredictable consequences. While not inherently destructive or financial, loading a URL can lead to malware execution, session hijacking, credential theft, or other harmful outcomes. The severity is high due to the blast radius of uncontrolled browser navigation in an AI agent context.
From the tool's definition 'Loads a URL' - navigates the browser to arbitrary web pages, which constitutes an external operation that can trigger side effects depending on the target URL (loading malicious sites, executing third-party scripts, etc.)
Attacks that exploit this kind of access
Loads a URL. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for navigate: 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 Chrome Devtools. Nothing to install.
navigate 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 navigate 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 navigate. 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.
navigate is provided by the Chrome Devtools MCP server (zhang77-x/chrpme_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 →