get_properties_by_category
AI agents call get_properties_by_category to retrieve information from CSS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve or list CSS property metadata filtered by category, consistent with the server's purpose of CSS analysis and documentation. The description is empty, lowering confidence slightly, but the naming pattern and sibling tools all perform queries without side effects. No evidence of executing code, modifying data, or destructive operations.
From the tool's definition Tool name 'get_properties_by_category' indicates retrieval of CSS properties organized by category. Server context shows read-only operations: 'analyze_css', 'get_browser_compatibility', 'get_docs', 'search_properties'.
Attacks that exploit this kind of access
get_properties_by_category. It is categorised as a Read tool in the CSS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the CSS MCP Server MCP server in PolicyLayer and add a rule for get_properties_by_category: 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 CSS MCP Server. Nothing to install.
get_properties_by_category 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_properties_by_category 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_properties_by_category. 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_properties_by_category is provided by the CSS MCP Server MCP server (lesleslie/css-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 →