humanize · Humanize MCP: Risk & Policy

WHAT IT DOES

What humanize does on HumanizeMCP

AI agents use humanize 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 humanize needs a policy

Based on the server description, 'humanize' almost certainly rewrites or transforms input text, which is a Write/modify operation. It does not delete data or execute code. Severity is medium because it could be misused to deceive AI detectors. Confidence is reduced due to the empty tool description.

From the tool's definition Tool name 'humanize' on a server described as one that 'rewrites AI-generated prose to appear human-authored' — the server's purpose implies text transformation/rewriting.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

humanize Rate-limited

humanize 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": {
    "humanize": {
      "limits": [
        {
          "counter": "humanize_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 humanize

What does the humanize tool do? +

humanize. 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 humanize? +

Register the Humanize MCP server in PolicyLayer and add a rule for humanize: 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 humanize? +

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

Can I rate-limit humanize? +

Yes. Add a rate_limit block to the humanize 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 humanize completely? +

Set action: deny in the PolicyLayer policy for humanize. 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 humanize? +

humanize 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.