AI agents call check_ssl_cert to retrieve information from Keel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
SSL certificate inspection is a standard network diagnostic query that reads metadata from a remote server. It does not alter state, execute code, delete data, or commit financial transactions. The only risk is information disclosure if sensitive certificate details are leaked, but this is minimal since certificates are typically public-facing and inspection is a normal administrative activity.
From the tool's definition Tool description states 'Inspect the SSL/TLS certificate on a host' — this is a query operation that retrieves certificate data without modifying systems or triggering side effects. No write, delete, execute, or financial operations are involved.
Attacks that exploit this kind of access
Inspect the SSL/TLS certificate on a host. It is categorised as a Read tool in the Keel MCP Server, which means it retrieves data without modifying state.
Register the Keel MCP server in PolicyLayer and add a rule for check_ssl_cert: 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 Keel. Nothing to install.
check_ssl_cert 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 check_ssl_cert 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 check_ssl_cert. 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.
check_ssl_cert is provided by the Keel MCP server (seayniclabs/keel). 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 →