AI agents use text_humanize to create or update resources in Tools — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tools environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
lang | string | — | Language (default: en) |
text | string | Yes | Text to humanize (max 3000 chars) |
style | string | — | Rewriting style (default: standard) |
Parameters from the server's own tool schema.
This tool modifies text content reversibly by rewriting it with different stylistic approaches. The capability to reduce AI detection rates suggests potential use in evading content provenance systems or facilitating deceptive communications (e.g., academic dishonesty, misleading content distribution). However, it does not delete data, execute code, or move money, placing it squarely in Write.
From the tool's definition Rewrite AI-generated text to sound naturally human-written. Reduces AI detection rates.
Attacks that exploit this kind of access
Rewrite AI-generated text to sound naturally human-written. Supports Chinese and English. Reduces AI detection rates. Styles: standard, casual, academic, creative. It is categorised as a Write tool in the Tools MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
text_humanize accepts 3 parameters: lang, text, style. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the Tools MCP server in PolicyLayer and add a rule for text_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 Tools. Nothing to install.
text_humanize 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 text_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.
Set action: deny in the PolicyLayer policy for text_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.
text_humanize is provided by the Tools MCP server (https://www.jiebang.site/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →