Stop heap sampling and get the memory profile
AI agents call stop-heap-sampling to retrieve information from Debugger MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool stops an ongoing heap sampling session and retrieves the resulting memory profile data. The primary action is collecting/reading profiling information. While it does stop an active process, the effect is simply terminating a monitoring session and returning data, not modifying or deleting any application state. The retrieved memory profile is read-only diagnostic information.
From the tool's definition Stop heap sampling and get the memory profile
Attacks that exploit this kind of access
Stop heap sampling and get the memory profile. It is categorised as a Read tool in the Debugger MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Debugger MCP Server MCP server in PolicyLayer and add a rule for stop-heap-sampling: 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 Debugger MCP Server. Nothing to install.
stop-heap-sampling 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 stop-heap-sampling 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 stop-heap-sampling. 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.
stop-heap-sampling is provided by the Debugger MCP Server MCP server (phoenixrr2113/debugger-mcp). 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 →