AI agents call skvil_catalog to retrieve information from Skvil without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays information from a catalog of certified skills. The verb 'browse' and the context of viewing a catalog are characteristic of Read operations. There is no indication of data modification, deletion, or execution of arbitrary code.
From the tool's definition Tool name 'skvil_catalog' and description 'Browse the full catalog of Skvil-certified AI agent skills with detailed...' indicate a query/browsing operation that retrieves and presents existing data without modification, deletion, or execution of external…
Attacks that exploit this kind of access
Browse the full catalog of Skvil-certified AI agent skills with detailed. It is categorised as a Read tool in the Skvil MCP Server, which means it retrieves data without modifying state.
Register the Skvil MCP server in PolicyLayer and add a rule for skvil_catalog: 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 Skvil. Nothing to install.
skvil_catalog 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 skvil_catalog 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 skvil_catalog. 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.
skvil_catalog is provided by the Skvil MCP server (skvil-ia/skvil-mcp). 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 →