Get variable scopes for a stack frame (DAP standard)
AI agents call scopes to retrieve information from MCP Chrome Debugger Protocol without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves variable scope information during debugging—a read-only operation that inspects data from a running Node.js process. While it does not modify or execute code, severity is elevated to 'high' because scope inspection could expose sensitive data (API keys, credentials, PII, internal state) that might be present in variables at any stack frame, making it a significant information disclosure risk if…
From the tool's definition Tool name 'scopes' and description 'Get variable scopes for a stack frame' indicates retrieval of debugging information.
Attacks that exploit this kind of access
Get variable scopes for a stack frame (DAP standard). It is categorised as a Read tool in the MCP Chrome Debugger Protocol MCP Server, which means it retrieves data without modifying state.
Register the MCP Chrome Debugger Protocol MCP server in PolicyLayer and add a rule for scopes: 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 Chrome Debugger Protocol. Nothing to install.
scopes is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scopes 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 scopes. 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.
scopes is provided by the MCP Chrome Debugger Protocol MCP server (vitalyostanin/mcp-chrome-debugger-protocol). 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 →