Validates whether a screen follows a given design token set. Checks colors, fonts, spacing, and border-radii against approved values and reports violations, compliance percentage, and suggestions for fixes.
AI agents call validate_design_system to retrieve information from Stitch MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only validation and analysis of design compliance. It inspects design artifacts (colors, fonts, spacing, border-radii) against a reference token set and reports findings, but does not modify, delete, or execute any operations. The output is informational (violations, compliance percentage, suggestions), making it a Read operation with minimal blast radius if misused.
From the tool's definition The tool 'validates' and 'checks' a design system against a set of tokens, 'reports violations' and provides 'suggestions' — pure inspection and analysis activities with no data modification or execution of external code.
Attacks that exploit this kind of access
Validates whether a screen follows a given design token set. Checks colors, fonts, spacing, and border-radii against approved values and reports violations, compliance percentage, and suggestions for fixes. It is categorised as a Read tool in the Stitch MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Stitch MCP Server MCP server in PolicyLayer and add a rule for validate_design_system: 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 Stitch MCP Server. Nothing to install.
validate_design_system 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 validate_design_system 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 validate_design_system. 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.
validate_design_system is provided by the Stitch MCP Server MCP server (oogleyskr/stitch-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
validate_design_system is one line of Stitch MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →