Quick preview of a design token system without full CSS output. Returns colors for light and/or dark mode, font pairing, radius, shadow style, WCAG contrast summary with near-failing pairs, design intent brief, and a visual preview URL on tokven.dev. Recommended first step: call this before gener...
Part of the Tokven MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_token_preview to retrieve information from Tokven without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_token_preview only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_token_preview:
rules:
- action: allowSee the full Tokven policy for all 5 tools.
Agents calling read-class tools like get_token_preview have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Quick preview of a design token system without full CSS output. Returns colors for light and/or dark mode, font pairing, radius, shadow style, WCAG contrast summary with near-failing pairs, design intent brief, and a visual preview URL on tokven.dev. Recommended first step: call this before generate_tokens so the user can approve the palette visually.. It is categorised as a Read tool in the Tokven MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_token_preview. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Tokven MCP server.
get_token_preview 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_token_preview rule in your Intercept 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 Intercept policy for get_token_preview. 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_token_preview is provided by the Tokven MCP server (tokven-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept