Search long-term memories in this MCP session namespace only.
AI agents call memory.search to retrieve information from ForLoop MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches existing memory data within a session namespace, which is a read-only operation. It retrieves information without side effects, modifying data, executing code, deleting records, or moving resources. The blast radius of misuse is minimal—an agent could only discover what memories exist, not alter them or trigger external operations.
From the tool's definition Tool name 'memory.search' and description 'Search long-term memories in this MCP session namespace only' indicate a query/retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Search long-term memories in this MCP session namespace only. It is categorised as a Read tool in the ForLoop MCP MCP Server, which means it retrieves data without modifying state.
Register the ForLoop 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 ForLoop MCP. 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 ForLoop MCP server (master0ffate/forloop-mcp). 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 →