AI agents call memory_search to retrieve information from Ruflo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only search operation on semantic memory. It retrieves or queries data without side effects, matching the definition of the Read category. The severity is low because searching memory poses minimal risk—it cannot modify state, execute arbitrary code, or cause destructive actions.
From the tool's definition Tool name 'memory_search' with description 'Search semantic memory using HNSW' indicates a query operation that retrieves data from a vector database using hierarchical navigable small world indexing.
Attacks that exploit this kind of access
Search semantic memory using HNSW. It is categorised as a Read tool in the Ruflo MCP Server, which means it retrieves data without modifying state.
Register the Ruflo MCP server in PolicyLayer and add a rule for memory_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 Ruflo. Nothing to install.
memory_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 memory_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 memory_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.
memory_search is provided by the Ruflo MCP server (ruvnet/ruflo). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
memory_search is one line of Ruflo's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →