AI agents call preview_description_cleaning to retrieve information from TAPD Data Fetcher without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool previews or simulates data cleaning without making any actual modifications. It retrieves and displays a preview of what cleaned data would look like, which is a read operation with no side effects. The server context (data fetching from TAPD) and the tool's explicit non-modifying nature place it firmly in the Read category with low severity.
From the tool's definition Tool description states '预览 description 字段清理效果，不实际修改数据' which translates to 'preview the effect of cleaning the description field, without actually modifying data'.
Documented attack patterns abuse exactly the kind of access preview_description_cleaning gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TAPD Data Fetcher, and nothing reaches the server without passing your rules. This is the rule we recommend for preview_description_cleaning:
{
"version": "1",
"default": "deny",
"tools": {
"preview_description_cleaning": {}
}
}preview_description_cleaning is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
预览 description 字段清理效果，不实际修改数据. It is categorised as a Read tool in the TAPD Data Fetcher MCP Server, which means it retrieves data without modifying state.
Register the TAPD Data Fetcher MCP server in PolicyLayer and add a rule for preview_description_cleaning: 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 TAPD Data Fetcher. Nothing to install.
preview_description_cleaning is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the preview_description_cleaning 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 preview_description_cleaning. 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.
preview_description_cleaning is provided by the TAPD Data Fetcher MCP server (onecuriouslearner/mcpagentre). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TAPD Data Fetcher, 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.
20 TAPD Data Fetcher tools catalogued and risk-classified — across an index of 43,000+ MCP servers.