AI agents use clean_text to create or update resources in Awesome-MCP-Scaffold — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Awesome-MCP-Scaffold environment.
The tool processes and transforms text (cleaning and normalizing), which constitutes a reversible modification of data. It does not read external data, execute code, delete anything, or involve finances. Severity is low as it only operates on provided text input with no system-level side effects.
From the tool's definition 'Clean and normalize text' — modifies input text by transforming it
Documented attack patterns abuse exactly the kind of access clean_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Awesome-MCP-Scaffold, and nothing reaches the server without passing your rules. This is the rule we recommend for clean_text:
{
"version": "1",
"default": "deny",
"tools": {
"clean_text": {
"limits": [
{
"counter": "clean_text_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}clean_text 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.
Clean and normalize text. It is categorised as a Write tool in the Awesome-MCP-Scaffold MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Awesome-MCP-Scaffold MCP server in PolicyLayer and add a rule for clean_text: 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 Awesome-MCP-Scaffold. Nothing to install.
clean_text 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 clean_text 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 clean_text. 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.
clean_text is provided by the Awesome-MCP-Scaffold MCP server (ww-ai-lab/awesome-mcp-scaffold). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Awesome-MCP-Scaffold, 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.
24 Awesome-MCP-Scaffold tools catalogued and risk-classified — across an index of 43,000+ MCP servers.