AI agents use add_paragraph to create or update resources in Wps — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wps environment.
This tool creates or modifies document content reversibly. It does not delete data (not Destructive), execute arbitrary code (not Execute), move money (not Financial), or merely retrieve data (not Read). Write is the appropriate category. Severity is medium because an AI agent misusing this could generate unwanted or malicious text content in documents, but the effect is reversible via undo or deletion.
From the tool's definition Tool name 'add_paragraph' and description 'Add a paragraph to an existing document' indicate creation/modification of document content. The server enables 'create and edit WPS Office documents' via natural language commands.
Attacks that exploit this kind of access
Add a paragraph to an existing document. It is categorised as a Write tool in the Wps MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wps MCP server in PolicyLayer and add a rule for add_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 Wps. Nothing to install.
add_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 add_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 add_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.
add_paragraph is provided by the Wps MCP server (xiao-rx/wps-mcp-server). 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 →