apply_style · Humanize MCP: Risk & Policy

WHAT IT DOES

What apply_style does on HumanizeMCP

AI agents use apply_style to create or update resources in HumanizeMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your HumanizeMCP environment.

WHY IT NEEDS A POLICY

Why apply_style needs a policy

The tool appears to apply transformations to text content, creating modified output. This is reversible (original content can be retained or reverted), making it Write rather than Destructive.

From the tool's definition Tool name 'apply_style' suggests modifying content by applying stylistic changes. Context indicates the server rewrites AI-generated prose; 'apply_style' likely creates or modifies text to alter its presentation or stylistic characteristics.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

apply_style Rate-limited

apply_style 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "apply_style": {
      "limits": [
        {
          "counter": "apply_style_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches HumanizeMCP, so you can run agents against it safely.

FAQ

Questions about apply_style

What does the apply_style tool do? +

apply_style. It is categorised as a Write tool in the HumanizeMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on apply_style? +

Register the Humanize MCP server in PolicyLayer and add a rule for apply_style: 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 HumanizeMCP. Nothing to install.

What risk level is apply_style? +

apply_style is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit apply_style? +

Yes. Add a rate_limit block to the apply_style 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.

How do I block apply_style completely? +

Set action: deny in the PolicyLayer policy for apply_style. 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.

What MCP server provides apply_style? +

apply_style is provided by the Humanize MCP server (kitfoxs/humanize-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.