Generate CSS/Tailwind configuration and setup instructions for a specific font. It will automatically attempt to download the font files for testing purposes, assuming you have a valid license.
AI agents use setup_font_config to create or update resources in Font MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Font MCP environment.
This tool creates configuration files (CSS/Tailwind setup instructions) and downloads font files to the local system, both reversible write operations. While it downloads files automatically, this is a modification of the project state rather than destructive action. The severity is medium because downloading large font files or misconfigured CSS could consume resources or break styling, but changes can be reverted.
From the tool's definition Tool description states it will 'Generate CSS/Tailwind configuration and setup instructions' and 'automatically attempt to download the font files'. The 'Generate' and 'download' operations create or modify files and configuration in the user's project.
Documented attack patterns abuse exactly the kind of access setup_font_config gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Font MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for setup_font_config:
{
"version": "1",
"default": "deny",
"tools": {
"setup_font_config": {
"limits": [
{
"counter": "setup_font_config_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}setup_font_config stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Generate CSS/Tailwind configuration and setup instructions for a specific font. It will automatically attempt to download the font files for testing purposes, assuming you have a valid license. It is categorised as a Write tool in the Font MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Font MCP server in PolicyLayer and add a rule for setup_font_config: 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 Font MCP. Nothing to install.
setup_font_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the setup_font_config 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 setup_font_config. 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.
setup_font_config is provided by the Font MCP server (microck/font-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Font MCP, 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 Font MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.