AI agents call gandi_cert_get_crt to retrieve information from Gandi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns data (the certificate PEM document) without creating, modifying, deleting, executing code, or moving money. The blast radius of misuse is minimal—an attacker gaining access would see certificate data that is typically already public or semi-public as part of standard TLS certificate validation. There are no destructive, financial, or execution-based consequences.
From the tool's definition The tool 'Fetch the raw issued certificate (PEM document)' performs a retrieval operation with no modifications or side effects. It retrieves an existing certificate document in standard PEM format.
Attacks that exploit this kind of access
Fetch the raw issued certificate (PEM document) for a certificate. It is categorised as a Read tool in the Gandi MCP Server, which means it retrieves data without modifying state.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_cert_get_crt: 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 Gandi. Nothing to install.
gandi_cert_get_crt 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 gandi_cert_get_crt 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 gandi_cert_get_crt. 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.
gandi_cert_get_crt is provided by the Gandi MCP server (millsymills-com/gandi-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 →