Step out of current function (DAP standard name)
AI agents invoke stepOut to trigger actions in MCP Chrome Debugger Protocol. 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.
stepOut controls execution flow of a running Node.js process via the Debug Adapter Protocol. It triggers an external operation (resuming execution out of the current function call frame) in the target process, which qualifies as Execute. Misuse could cause the debugged process to advance past breakpoints or critical inspection points, potentially skipping error handling or security checks.
From the tool's definition Step out of current function (DAP standard name)
Attacks that exploit this kind of access
Step out of current function (DAP standard name). It is categorised as a Execute tool in the MCP Chrome Debugger Protocol MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Chrome Debugger Protocol MCP server in PolicyLayer and add a rule for stepOut: 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.
stepOut 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 stepOut 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 stepOut. 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.
stepOut 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 →