AI agents call memstem_list_skills 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 retrieves and enumerates skill metadata from the knowledge store. It performs no write, delete, or execute operations—merely listing/reading existing data. The scope filtering is a query parameter, not a destructive or modifying operation. Blast radius is minimal: worst case, an agent learns what skills exist, which is low-risk information disclosure.
From the tool's definition Tool name 'list' and description 'List available skills' indicate a query/retrieval operation with no modification or side effects. Returns information about available skills filtered by scope.
Attacks that exploit this kind of access
List available skills, optionally filtered by scope. 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_list_skills: 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_list_skills 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_list_skills 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_list_skills. 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_list_skills 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 →