List all design tokens, optionally filtered by type (color, dimension, fontFamily, etc.)
AI agents call list_tokens to retrieve information from Ds Pilot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries design token metadata without side effects. It enables read-only access to the design system's token catalog, which is necessary for AI agents to reference existing tokens but poses no risk of data modification, deletion, or external system changes. The low severity reflects that exposure of design token definitions is informational only.
From the tool's definition Tool name 'list_tokens' and description 'List all design tokens' indicate a retrieval operation with no modification capability. The optional filtering by type (color, dimension, fontFamily, etc.) is a query parameter that does not alter data.
Documented attack patterns abuse exactly the kind of access list_tokens gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ds Pilot, and nothing reaches the server without passing your rules. This is the rule we recommend for list_tokens:
{
"version": "1",
"default": "deny",
"tools": {
"list_tokens": {}
}
}list_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.
List all design tokens, optionally filtered by type (color, dimension, fontFamily, etc.). It is categorised as a Read tool in the Ds Pilot MCP Server, which means it retrieves data without modifying state.
Register the Ds Pilot MCP server in PolicyLayer and add a rule for list_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 Ds Pilot. Nothing to install.
list_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 list_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 list_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.
list_tokens is provided by the Ds Pilot MCP server (lyse-labs/ds-pilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ds Pilot, 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 Ds Pilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.