AI agents call memento_pmg_what_might_break 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 is a read-only query that traverses dependency graphs to report on potential impact relationships. The word 'Find' and the parenthetical 'impact analysis' describe information retrieval and analysis, not side effects. The [DEPRECATED] marker suggests it is no longer actively maintained but does not change its functional category.
From the tool's definition Tool name and description indicate 'Find all entities that depend on the given entity (impact analysis)' — a dependency query operation that retrieves and analyzes relationships without modifying or executing actions.
Attacks that exploit this kind of access
[DEPRECATED] Find all entities that depend on the given entity (impact analysis). 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_what_might_break: 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_what_might_break 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_what_might_break 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_what_might_break. 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_what_might_break 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 →