Retrieves the current call stack when execution is paused.
AI agents call get_call_stack to retrieve information from MCP JS Debugger without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves information about the call stack during a paused debugging session. It performs no side effects, does not execute code, does not modify state, and does not delete or move data. It is a pure information retrieval operation, consistent with the 'Read' category.
From the tool's definition Tool name 'get_call_stack' and description 'Retrieves the current call stack when execution is paused' indicate a read-only operation that queries debugging state without modifying or executing code.
Attacks that exploit this kind of access
Retrieves the current call stack when execution is paused. It is categorised as a Read tool in the MCP JS Debugger MCP Server, which means it retrieves data without modifying state.
Register the MCP JS Debugger MCP server in PolicyLayer and add a rule for get_call_stack: 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 JS Debugger. Nothing to install.
get_call_stack 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_call_stack 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_call_stack. 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_call_stack is provided by the MCP JS Debugger MCP server (johngrimes/mcp-js-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 →