AI agents call memory_search to retrieve information from Terminal without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches and retrieves memory entries based on keywords, which is a read-only operation with no side effects. It does not create, modify, delete, or execute anything. The blast radius of misuse is minimal—an agent could search for sensitive memory content but cannot alter or act upon it without using other tools like memory_delete or run_command.
From the tool's definition Tool name 'memory_search' and description 'Search across all memories by keyword' indicate a query operation that retrieves stored data without modification or execution.
Attacks that exploit this kind of access
Search across all memories by keyword. It is categorised as a Read tool in the Terminal MCP Server, which means it retrieves data without modifying state.
Register the Terminal 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 Terminal. 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 Terminal MCP server (koushikmaji31/terminal-mcp-agent). 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 →