AI agents call memory_auto_test to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only testing/inspection tool. It extracts and returns memory data from text input without any side effects, persistence, or state changes. The emphasis on 'WITHOUT saving anything' confirms it has no write or destructive impact. Low severity because misuse would only expose analysis results, not cause harm.
From the tool's definition Tool description states 'Test memory extraction on text WITHOUT saving anything' and 'Returns what would be extracted' — it explicitly does not modify, delete, or execute operations. It only analyzes and returns data.
Attacks that exploit this kind of access
Test memory extraction on text WITHOUT saving anything. Returns what would be extracted. Useful for tuning prompts and checking provider output. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_auto_test: 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 Mementos. Nothing to install.
memory_auto_test 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 memory_auto_test 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 memory_auto_test. 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.
memory_auto_test is provided by the Mementos MCP server (@hasna/mementos). 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 →