Get detailed information about a memory including its schema, stats, and sample data.
AI agents call describe_memory to retrieve information from Structured-sh without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns metadata and sample information about an existing memory object. There is no creation, modification, deletion, or execution of code. The worst-case misuse would be information disclosure of sample data within the memory, which poses only low risk depending on what data samples might be present.
From the tool's definition The tool description states it retrieves 'detailed information about a memory including its schema, stats, and sample data' - purely informational operations without modification or side effects.
Attacks that exploit this kind of access
Get detailed information about a memory including its schema, stats, and sample data. It is categorised as a Read tool in the Structured-sh MCP Server, which means it retrieves data without modifying state.
Register the Structured-sh MCP server in PolicyLayer and add a rule for describe_memory: 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 Structured-sh. Nothing to install.
describe_memory 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 describe_memory 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 describe_memory. 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.
describe_memory is provided by the Structured-sh MCP server (structured-sh/structured). 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 →