AI agents call resuml_render to retrieve information from Resuml without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves resume data, applies formatting/theming, and outputs HTML. No data is created, modified, deleted, or executed in ways that could trigger external side effects. The operation is purely presentational and reversible. This is a classic Read category operation (query/fetch/transform for display purposes).
From the tool's definition Tool name is 'resuml_render' and description states 'Render a resume to HTML using a specified theme' — this is a read-only operation that transforms input data into viewable output without modifying or deleting underlying data.
Attacks that exploit this kind of access
Render a resume to HTML using a specified theme. It is categorised as a Read tool in the Resuml MCP Server, which means it retrieves data without modifying state.
Register the Resuml MCP server in PolicyLayer and add a rule for resuml_render: 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 Resuml. Nothing to install.
resuml_render 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 resuml_render 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 resuml_render. 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.
resuml_render is provided by the Resuml MCP server (resuml). 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 →