AI agents call memento_search 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 queries and retrieves data from the Memento memory store. The three modes described (basic FTS, advanced vNext pipeline, explain routing trace) are all read-only operations: full-text search retrieves matching memories, the advanced pipeline likely returns ranked or processed results, and explain mode traces query routing. No data is created, modified, deleted, or used to trigger external side effects.
From the tool's definition Tool name 'memento_search' combined with description 'Search memories' with modes for full-text search (FTS), advanced pipeline, and explain/routing trace—all retrieval and introspection operations with no mutation or execution capability.
Attacks that exploit this kind of access
Search memories. Modes: basic (FTS), advanced (vNext pipeline), explain (routing trace). 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: 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 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 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. 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 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 →