AI agents call memos_search 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.
Search tools query and retrieve data without side effects. The naming pattern and sibling tool context (recent, remember) indicate this retrieves memos/notes. No indication of modification, deletion, or execution capabilities. Low severity because read operations have minimal blast radius when misused.
From the tool's definition Tool name is 'memos_search' which indicates a search/query operation. Description is empty, limiting certainty, but the context shows this is part of a notes/memos system where sibling tools are 'memos_recent' and 'memos_remember' — all read-oriented.
Attacks that exploit this kind of access
memos_search. 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_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 Memos. Nothing to install.
memos_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 memos_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 memos_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.
memos_search 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 →