AI agents use edit_paragraph to create or update resources in LuzzyTool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LuzzyTool environment.
This tool creates or modifies document content reversibly. While it performs deletion and modification operations, these are within a document editing context and are not permanent/irreversible in nature (typical document edits can be undone or reverted). This places it in the Write category rather than Destructive.
From the tool's definition Tool description states '增删改操作' (add/delete/modify operations) on specific paragraphs in documents. The description explicitly indicates the tool modifies target paragraphs ('只修改目标段落').
Attacks that exploit this kind of access
【精确编辑】对文档中的特定段落执行增删改操作,只修改目标段落而不影响文件其他部分。. It is categorised as a Write tool in the LuzzyTool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LuzzyTool MCP server in PolicyLayer and add a rule for edit_paragraph: 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 LuzzyTool. Nothing to install.
edit_paragraph 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 edit_paragraph 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 edit_paragraph. 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.
edit_paragraph is provided by the LuzzyTool MCP server (luzzymeow/luzzytool). 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 →