AI agents call memento_search_vnext 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/queries data from the Memento memory system. The word 'search' combined with 'return' indicates a pure read operation. Despite the [DEPRECATED] status, the function performs no writes, deletes, or side effects—it only queries and returns structured results. The low severity reflects that searching memories poses minimal risk compared to writing, executing, or destructive operations.
From the tool's definition Tool name contains 'search' and description explicitly states 'Search memories' and 'return a structured bundle'—classic read operation with no modification or deletion.
Attacks that exploit this kind of access
[DEPRECATED] Search memories using the vNext retrieval pipeline and return a structured bundle. 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_search_vnext: 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_search_vnext 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_search_vnext 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_search_vnext. 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_search_vnext 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 →