AI agents invoke text_template to trigger actions in Onion. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Template rendering executes a transformation process by substituting variables into a template. While it doesn't run arbitrary code or shell commands, it does perform a dynamic operation whose output depends on its arguments. It is closer to Execute (transform/render) than Write (no persistent data creation) or Read (it produces output, not retrieves it).
From the tool's definition 简单模板渲染，将 {变量名} 替换为对应值 — template rendering by substituting named variables
Attacks that exploit this kind of access
简单模板渲染，将 {变量名} 替换为对应值。. It is categorised as a Execute tool in the Onion MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Onion MCP server in PolicyLayer and add a rule for text_template: 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 Onion. Nothing to install.
text_template is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the text_template 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 text_template. 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.
text_template is provided by the Onion MCP server (onion-ai/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
text_template is one line of Onion's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →