AI agents call memstem_search to retrieve information from Memstem without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information retrieval only—searching across stored memories and skills using hybrid keyword and semantic matching. There is no indication it modifies, deletes, executes code, or commits financial transactions. The operation is read-only and returns results without side effects, placing it clearly in the 'Read' category with low severity.
From the tool's definition Tool name 'memstem_search' and description 'Hybrid keyword + semantic search across memories and skills' indicate a search/query operation with no data modification or side effects.
Attacks that exploit this kind of access
Hybrid keyword + semantic search across memories and skills. It is categorised as a Read tool in the Memstem MCP Server, which means it retrieves data without modifying state.
Register the Memstem MCP server in PolicyLayer and add a rule for memstem_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 Memstem. Nothing to install.
memstem_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 memstem_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 memstem_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.
memstem_search is provided by the Memstem MCP server (memstem/memstem). 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 →