Search memento vault notes before answering questions about past decisions, prior fixes, project history, session context, recurring patterns, or exact identifiers. Use memento_get after search when you need full content for a returned path; do not use search to read a known note path.
AI agents call memento_search to retrieve information from Memento Vault without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a knowledge vault and returns search results without altering, deleting, or executing any code. It is a pure read operation with no side effects. The low severity reflects that searching stored notes poses minimal risk even if misused by an agent, as no data is modified, deleted, or used to trigger external actions.
From the tool's definition Tool name 'memento_search' and description 'Search memento vault notes' — explicit retrieval operation with no modification capability.
Documented attack patterns abuse exactly the kind of access memento_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Memento Vault, and nothing reaches the server without passing your rules. This is the rule we recommend for memento_search:
{
"version": "1",
"default": "deny",
"tools": {
"memento_search": {}
}
}memento_search is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search memento vault notes before answering questions about past decisions, prior fixes, project history, session context, recurring patterns, or exact identifiers. Use memento_get after search when you need full content for a returned path; do not use search to read a known note path. It is categorised as a Read tool in the Memento Vault MCP Server, which means it retrieves data without modifying state.
Register the Memento Vault 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 Vault. 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 Vault MCP server (sandsower/memento-vault). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Memento Vault, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Memento Vault tools catalogued and risk-classified — across an index of 43,000+ MCP servers.