Download design tokens for a project or styleguide
AI agents call get_design_tokens to retrieve information from Zeplin MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves design token data (styling constants, color palettes, typography rules, etc.) from Zeplin for use in code generation. It performs a read-only query operation with no ability to modify, delete, or execute external operations. The 'download' verb here means fetching data, not destructive action. Misuse by an AI agent would only expose design specifications, not compromise systems or data integrity.
From the tool's definition Tool name 'get_design_tokens' and description 'Download design tokens for a project or styleguide' indicate data retrieval with no modification or side effects.
Documented attack patterns abuse exactly the kind of access get_design_tokens gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zeplin MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_design_tokens:
{
"version": "1",
"default": "deny",
"tools": {
"get_design_tokens": {}
}
}get_design_tokens is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Download design tokens for a project or styleguide. It is categorised as a Read tool in the Zeplin MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zeplin MCP Server MCP server in PolicyLayer and add a rule for get_design_tokens: 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 Zeplin MCP Server. Nothing to install.
get_design_tokens 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_tokens 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_tokens. 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_tokens is provided by the Zeplin MCP Server MCP server (zeplin/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Zeplin MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 Zeplin MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.