AI agents call memos_recent to retrieve information from Memos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without an explicit description, inference relies on naming convention and context. 'Recent' typically indicates a query for recently-added or recently-modified items. No modification, deletion, execution, or financial operations are implied. This is a straightforward data retrieval tool with low blast radius—misuse would retrieve stale or unintended memos rather than cause harm.
From the tool's definition Tool name 'memos_recent' suggests retrieval of recent memos/notes. Combined with sibling tools 'memos_remember' (write) and 'memos_search' (read), this tool follows a read pattern.
Attacks that exploit this kind of access
memos_recent. It is categorised as a Read tool in the Memos MCP Server, which means it retrieves data without modifying state.
Register the Memos MCP server in PolicyLayer and add a rule for memos_recent: 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 Memos. Nothing to install.
memos_recent 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 memos_recent 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 memos_recent. 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.
memos_recent is provided by the Memos MCP server (mchosc/memos-mcp-server). 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 →