AI agents call memento_pmg_summary to retrieve information from Memento without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregated information from a local graph database for inspection purposes. The summary operation is read-only and non-destructive. Although marked [DEPRECATED], it remains a query function. The deprecation status does not elevate severity—if anything, it suggests lower operational impact.
From the tool's definition Tool performs a query operation ('Get a summary') that retrieves and reports on existing data in the Project Memory Graph without modifying, deleting, or executing operations.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
[DEPRECATED] Get a summary of the entire Project Memory Graph (all entities and recent relations). It is categorised as a Read tool in the Memento MCP Server, which means it retrieves data without modifying state.
Register the Memento MCP server in PolicyLayer and add a rule for memento_pmg_summary: 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 Memento. Nothing to install.
memento_pmg_summary 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 memento_pmg_summary 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 memento_pmg_summary. 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.
memento_pmg_summary is provided by the Memento MCP server (joyciakira/memento). 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 →