AI agents call memory_synthesis_status 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 tool queries the status of existing synthesis runs without creating, modifying, deleting, or executing any operations. It is a pure read operation similar to status checks or monitoring queries. The low severity reflects that retrieving status information poses minimal risk to system integrity or data safety.
From the tool's definition Tool name 'memory_synthesis_status' and description 'Get the status of synthesis runs' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the status of synthesis runs. 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_synthesis_status: 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_synthesis_status 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_synthesis_status 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_synthesis_status. 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_synthesis_status 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 →