AI agents call memento_kg 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.
The tool performs read-only operations on a knowledge graph and system health monitoring. While it could provide sensitive information about agent memory and goals to an unauthorized user (raising severity above 'low'), it does not modify data, execute code, or cause destructive effects. Classified as Read.
From the tool's definition Tool description states 'Knowledge Graph operations. Actions: extract, health, cross_workspace_stats.' All listed actions are informational queries: 'extract' retrieves knowledge graph data, 'health' checks status, and 'cross_workspace_stats' aggregates…
Attacks that exploit this kind of access
Knowledge Graph operations. Actions: extract, health, cross_workspace_stats. 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_kg: 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_kg 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_kg 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_kg. 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_kg 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 →