AI agents call examine_memory to retrieve information from Rr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays memory contents for debugging purposes in an rr reverse debugger session. It does not modify memory, execute code, or cause side effects—it is a passive inspection capability. Memory examination is standard in debuggers and carries minimal security risk when the user already has access to the debugging session.
From the tool's definition Tool name 'examine_memory' and description 'Examine raw memory at an address. Use to inspect' indicate data retrieval without modification or execution. The verb 'examine' and 'inspect' denote read-only access.
Attacks that exploit this kind of access
Examine raw memory at an address. Use to inspect. It is categorised as a Read tool in the Rr MCP Server, which means it retrieves data without modifying state.
Register the Rr MCP server in PolicyLayer and add a rule for examine_memory: 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 Rr. Nothing to install.
examine_memory 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 examine_memory 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 examine_memory. 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.
examine_memory is provided by the Rr MCP server (jnjaeschke/rr-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 →