AI agents call get_design_system_summary 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 'get_' prefix, combined with context from sibling tools and the server's purpose of managing artifacts and design systems, indicates this retrieves or queries design system metadata without modifying or executing anything. No side effects are apparent. Confidence is slightly reduced due to the absent description, but the naming pattern and server context strongly support Read classification.
From the tool's definition Tool name 'get_design_system_summary' indicates a retrieval operation ('get'). No description provided, but the pattern is consistent with sibling tools like 'get_artifact', 'get_artifact_schema', and 'get_local_model_status', which are all read operations.
Attacks that exploit this kind of access
get_design_system_summary. 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 get_design_system_summary: 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.
get_design_system_summary 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 get_design_system_summary 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 get_design_system_summary. 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.
get_design_system_summary 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 →