AI agents use create_tag to create or update resources in MCP Auth — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Auth environment.
Creating a tag is a reversible write operation that adds data to the system. It is not destructive (tags can be deleted), does not execute arbitrary code, and has no financial impact. The blast radius is low because tag creation is typically isolated to metadata and does not affect core application state or user data access control.
From the tool's definition Tool name is 'create_tag' and description states 'Create a new tag'. The verb 'Create' indicates a write operation that modifies state by adding a new tag resource.
Attacks that exploit this kind of access
Create a new tag. It is categorised as a Write tool in the MCP Auth MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Auth MCP server in PolicyLayer and add a rule for create_tag: 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 MCP Auth. Nothing to install.
create_tag 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 create_tag 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 create_tag. 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.
create_tag is provided by the MCP Auth MCP server (rubenpenap/mcp-auth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
create_tag is one line of MCP Auth's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →