AI agents call memory_search_hybrid to retrieve information from Mementos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Memory_search_hybrid retrieves and ranks memory records using two search modalities (keyword FTS5 and semantic embedding) combined via RRF. This is fundamentally a read operation that queries existing data without creating, modifying, or deleting any state.
From the tool's definition Tool performs 'hybrid search combining keyword and semantic search' - a retrieval operation with 'no side effects'. The description explicitly indicates this is a search function, which is a query/read operation.
Attacks that exploit this kind of access
Hybrid search combining keyword (FTS5) and semantic (embedding) search using Reciprocal Rank Fusion (RRF). Best of both worlds: keyword precision + semantic recall. It is categorised as a Read tool in the Mementos MCP Server, which means it retrieves data without modifying state.
Register the Mementos MCP server in PolicyLayer and add a rule for memory_search_hybrid: 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 Mementos. Nothing to install.
memory_search_hybrid 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 memory_search_hybrid 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 memory_search_hybrid. 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.
memory_search_hybrid is provided by the Mementos MCP server (@hasna/mementos). 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 →