WordPress에 새 태그를 생성합니다.
AI agents use createTag to create or update resources in WordPress MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your WordPress MCP Server environment.
The tool performs a CREATE operation on WordPress tags, which is a write operation that modifies the WordPress database by adding new taxonomy terms. While reversible (tags can be deleted), it does modify state. It is not destructive (deletion is handled separately by 'deleteTag'), not financial, and not execute-level code/command triggering.
From the tool's definition Tool name is 'createTag' and description states it creates ('생성합니다') a new tag in WordPress. This is a reversible create operation on WordPress taxonomy data.
Attacks that exploit this kind of access
WordPress에 새 태그를 생성합니다. It is categorised as a Write tool in the WordPress MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the WordPress MCP Server MCP server in PolicyLayer and add a rule for createTag: 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 WordPress MCP Server. Nothing to install.
createTag 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 createTag 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 createTag. 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.
createTag is provided by the WordPress MCP Server MCP server (ssong-openmaru-io/ai-mcp-wordpress). 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 →