AI agents call list_themes to retrieve information from Web Gui without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'list_themes' tool retrieves or enumerates available themes. This is a read-only operation with no side effects. Despite the empty description reducing confidence slightly, the semantic meaning of 'list' combined with the server's artifact/UI rendering purpose indicates a simple data retrieval function. There is no indication of modification, execution, deletion, or financial impact.
From the tool's definition Tool name 'list_themes' implies retrieval/enumeration of theme data. The server context involves HTML generation and artifact management. 'list' is a canonical Read operation with no mutation.
Attacks that exploit this kind of access
list_themes. It is categorised as a Read tool in the Web Gui MCP Server, which means it retrieves data without modifying state.
Register the Web Gui MCP server in PolicyLayer and add a rule for list_themes: 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 Web Gui. Nothing to install.
list_themes 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_themes 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_themes. 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_themes is provided by the Web Gui MCP server (thehzuo/gui-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 →