AI agents call skills_discover to retrieve information from Ensemble without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs information discovery by scanning and returning matching skills based on semantic search. It retrieves or queries data without side effects, side-stepping execution of any discovered skills. The action is read-only: scanning locations and returning results. No data is created, modified, deleted, or executed as a direct consequence of this tool's operation.
From the tool's definition Tool description states 'Scan tool-native skill locations and return relevant skills via semantic search' — a retrieval and query operation with no data modification or execution of discovered skills.
Attacks that exploit this kind of access
Scan tool-native skill locations and return relevant skills via semantic search. It is categorised as a Read tool in the Ensemble MCP Server, which means it retrieves data without modifying state.
Register the Ensemble MCP server in PolicyLayer and add a rule for skills_discover: 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 Ensemble. Nothing to install.
skills_discover 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 skills_discover 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 skills_discover. 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.
skills_discover is provided by the Ensemble MCP server (lynkbyte/ensemble). 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 →