AI agents call memory_recall 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 retrieves data from a memory store without side effects. It performs a lookup/fetch operation analogous to a database query. No data is modified, deleted, or executed. The ability to recall memory could be sensitive depending on what data is stored, but the tool itself is non-destructive and read-only, making it a Read category risk with low severity.
From the tool's definition Tool name 'memory_recall' and description 'Retrieve a specific memory by name' indicate a read-only operation that queries stored memory without modification, deletion, or execution.
Attacks that exploit this kind of access
Retrieve a specific memory by name. 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_recall: 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_recall 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_recall 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_recall. 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_recall 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 →