AI agents call get_design_token to retrieve information from Spindle without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves design system tokens (colors, typography, spacing, etc.) without modifying, executing, or deleting anything. It is purely informational, consistent with the other sibling tools on this design system server (get_component_info, get_icons, etc.) which are all read operations. No side effects or risks to data integrity.
From the tool's definition Tool name 'get_design_token' and description 'retrieves design tokens of a specified type' indicate a read-only operation. The verb 'get' and the absence of any modification language confirm this is a data retrieval function.
Attacks that exploit this kind of access
指定した種類のデザイントークンを取得します. It is categorised as a Read tool in the Spindle MCP Server, which means it retrieves data without modifying state.
Register the Spindle MCP server in PolicyLayer and add a rule for get_design_token: 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 Spindle. Nothing to install.
get_design_token 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_token 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_token. 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_token is provided by the Spindle MCP server (@openameba/spindle-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.