AI agents call inspect_scopes to retrieve information from Node Js Debugger MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves debugging state information (variable scopes) without modifying application code or data. It is categorized as Read because it queries runtime state. Severity is high because scope inspection can expose sensitive variables, secrets, authentication tokens, or other private data that an AI agent might extract and misuse, despite the tool itself being non-destructive.
From the tool's definition Tool name 'inspect_scopes' combined with server's stated debugging capabilities (variable inspection, expression evaluation, console monitoring) and sibling tools like 'get_object_properties', 'list_call_stack', and 'get_pause_info' all indicate read-only…
Documented attack patterns abuse exactly the kind of access inspect_scopes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Node Js Debugger MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for inspect_scopes:
{
"version": "1",
"default": "deny",
"tools": {
"inspect_scopes": {}
}
}inspect_scopes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
inspect_scopes. It is categorised as a Read tool in the Node Js Debugger MCP MCP Server, which means it retrieves data without modifying state.
Register the Node Js Debugger MCP server in PolicyLayer and add a rule for inspect_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 Node Js Debugger MCP. Nothing to install.
inspect_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 inspect_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 inspect_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.
inspect_scopes is provided by the Node Js Debugger MCP server (scriptedalchemy/devtools-debugger-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 21 Node Js Debugger MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
21 Node Js Debugger MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.