Get variables (scope is variablesReference: number)
AI agents call get_variables to retrieve information from Mcp Debugger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves variable values from a running process during a debug session. It has no side effects on the debugged application or external systems. However, severity is medium rather than low because variables may contain sensitive data (credentials, API keys, personal information), and an AI agent could extract such information without the user's knowledge.
From the tool's definition Tool name is 'get_variables' and description states 'Get variables (scope is variablesReference: number)'. This retrieves variable state during a debugging session without modifying execution or data.
Attacks that exploit this kind of access
Get variables (scope is variablesReference: number). It is categorised as a Read tool in the Mcp Debugger MCP Server, which means it retrieves data without modifying state.
Register the Mcp Debugger MCP server in PolicyLayer and add a rule for get_variables: 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 Debugger. Nothing to install.
get_variables 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 get_variables 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 get_variables. 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.
get_variables is provided by the Mcp Debugger MCP server (@debugmcp/mcp-debugger). 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 →