AI agents call verify_setup to retrieve information from SkillMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/inspection tool that gathers configuration and state information for monitoring purposes. It does not modify data, execute code, trigger external operations, delete anything, or involve financial transactions. The described functionality—checking paths, counting skills, and verifying registration status—are all read-only queries with no capability for side effects or system changes.
From the tool's definition Tool performs a 'health snapshot' that retrieves and queries status information (paths, skill counts, registration status) with no side effects or data modification.
Attacks that exploit this kind of access
One-call health snapshot: paths, skill counts, and registration status. It is categorised as a Read tool in the SkillMCP MCP Server, which means it retrieves data without modifying state.
Register the Skill MCP server in PolicyLayer and add a rule for verify_setup: 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 SkillMCP. Nothing to install.
verify_setup 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 verify_setup 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 verify_setup. 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.
verify_setup is provided by the Skill MCP server (nventimiglia/skillsmcp). 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 →