Disconnect from current web page and release browser resources
AI agents invoke web_disconnect to trigger actions in Web 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 terminates an active browser session and releases associated resources. It triggers an external operation (disconnecting from a browser/page) that affects the runtime environment. While not destructive to persistent data, it irreversibly ends the current session state (unsaved form data, session context, etc.) and could disrupt ongoing automation workflows.
From the tool's definition 'Disconnect from current web page and release browser resources'
Attacks that exploit this kind of access
Disconnect from current web page and release browser resources. It is categorised as a Execute tool in the Web Bridge MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Web Bridge MCP server in PolicyLayer and add a rule for web_disconnect: 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 Web Bridge. Nothing to install.
web_disconnect 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 web_disconnect 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 web_disconnect. 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.
web_disconnect is provided by the Web Bridge MCP server (@midscene/web-bridge-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 →