AI agents call html_show to retrieve information from Llama without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries existing HTML content without any side effects. The verb 'Read' and the absence of any modification, deletion, or execution language clearly place it in the Read category. The severity is low because viewing HTML content has minimal blast radius—it only exposes data that is already stored, with no ability to alter state or trigger external operations.
From the tool's definition Tool name 'html_show' and description 'Read the current hand-authored HTML' explicitly indicate data retrieval with no modification capability.
Attacks that exploit this kind of access
Read the current hand-authored HTML. It is categorised as a Read tool in the Llama MCP Server, which means it retrieves data without modifying state.
Register the Llama MCP server in PolicyLayer and add a rule for html_show: 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 Llama. Nothing to install.
html_show 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 html_show 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 html_show. 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.
html_show is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →