Generate a preview PDF for a DocRenders template using its built-in preview_fields data. Returns a signed download URL. Previews are cached — repeated calls for the same template return instantly. Does not count against your render quota.
AI agents invoke render_template_preview to trigger actions in Docrenders. 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.
This tool executes an external operation (PDF rendering via the DocRenders API) that depends on template arguments. While it reads/previews content and does not count against quota, it triggers a real external service call and returns a signed URL. It doesn't modify persistent data (Write) or destroy anything (Destructive), but it does execute an external rendering process, placing it in Execute.
From the tool's definition 'Generate a preview PDF for a DocRenders template' and 'Returns a signed download URL' — triggers external PDF generation operation via DocRenders API
Attacks that exploit this kind of access
Generate a preview PDF for a DocRenders template using its built-in preview_fields data. Returns a signed download URL. Previews are cached — repeated calls for the same template return instantly. Does not count against your render quota. It is categorised as a Execute tool in the Docrenders MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docrenders MCP server in PolicyLayer and add a rule for render_template_preview: 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 Docrenders. Nothing to install.
render_template_preview 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 render_template_preview 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 render_template_preview. 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.
render_template_preview is provided by the Docrenders MCP server (jwhist/docrenders-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 →