Set a breakpoint.
AI agents use break_at to create or update resources in WineDbg MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WineDbg MCP Server environment.
Setting a breakpoint modifies the debugger's internal state (and the target process's memory via int3 or hardware debug registers) in a reversible way. It does not execute arbitrary code or irreversibly destroy data. The corresponding delete_breakpoint tool exists, confirming reversibility. Severity is medium because misuse could interfere with a running process being debugged.
From the tool's definition 'Set a breakpoint' — creates a new breakpoint entry in the debugger state
Attacks that exploit this kind of access
Set a breakpoint. It is categorised as a Write tool in the WineDbg MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WineDbg MCP Server MCP server in PolicyLayer and add a rule for break_at: 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 WineDbg MCP Server. Nothing to install.
break_at is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the break_at 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 break_at. 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.
break_at is provided by the WineDbg MCP Server MCP server (maci0/mcp-winedbg). 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 →