AI agents call pylon_get_ticket_forms to retrieve information from Pylon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves ticket form data without creating, modifying, deleting, or executing any operations. It has no side effects and presents no blast radius if called by an AI agent—the worst case is returning unnecessary or sensitive form metadata that an agent doesn't need, which is a minor information disclosure risk at most.
From the tool's definition Tool name and description indicate data retrieval: 'Get all ticket submission forms available to customers' uses the verb 'Get', which is a read-only operation that retrieves information without modification or side effects.
Attacks that exploit this kind of access
Get all ticket submission forms available to customers. It is categorised as a Read tool in the Pylon MCP Server, which means it retrieves data without modifying state.
Register the Pylon MCP server in PolicyLayer and add a rule for pylon_get_ticket_forms: 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 Pylon. Nothing to install.
pylon_get_ticket_forms 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 pylon_get_ticket_forms 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 pylon_get_ticket_forms. 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.
pylon_get_ticket_forms is provided by the Pylon MCP server (@customer-support-success/pylon-mcp-server). 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 →