Close the browser and cleanup resources
AI agents invoke Browser-Close to trigger actions in MCP GitHub Login Automation 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.
Closing a browser session and cleaning up resources is an execution action that terminates a running process. While not destructive to persistent data, it irreversibly ends the current browser session (including any unsaved state, active sessions, or in-progress operations), which could have meaningful side effects in an automation context.
From the tool's definition 'Close the browser and cleanup resources' — terminates a running browser process and frees associated resources
Attacks that exploit this kind of access
Close the browser and cleanup resources. It is categorised as a Execute tool in the MCP GitHub Login Automation Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP GitHub Login Automation Server MCP server in PolicyLayer and add a rule for Browser-Close: 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 GitHub Login Automation Server. Nothing to install.
Browser-Close 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 Browser-Close 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 Browser-Close. 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.
Browser-Close is provided by the MCP GitHub Login Automation Server MCP server (nikhil-kandekar/mcp-server-demo). 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 →