AI agents call list_templates to retrieve information from RendrKit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries template metadata to help users discover available templates and their schemas. It is purely informational with no capacity to modify data, execute commands, or trigger financial transactions. The blast radius of misuse is minimal — an attacker gains only knowledge of available templates.
From the tool's definition Tool name 'list_templates' and description explicitly states it 'List[s] all available image templates' — a retrieval operation with no modification, deletion, or execution of external operations. No side effects.
Attacks that exploit this kind of access
List all available image templates with their slot definitions. Use this to discover which templates exist and what slots they accept for direct rendering with generate_image. It is categorised as a Read tool in the RendrKit MCP Server, which means it retrieves data without modifying state.
Register the RendrKit MCP server in PolicyLayer and add a rule for list_templates: 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 RendrKit. Nothing to install.
list_templates 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 list_templates 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 list_templates. 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.
list_templates is provided by the RendrKit MCP server (vbiff/rendrkit-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 →