AI agents use airbyte_create_tag to create or update resources in Airbyte — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Airbyte environment.
This tool creates a new tag, which is a reversible write operation. Tags in Airbyte are organizational metadata with minimal blast radius if misused—an agent could create unwanted tags, but this causes no data loss, financial impact, or system damage. The operation is easily reversible by deleting the tag. Severity is low because tag creation is a low-impact administrative action.
From the tool's definition Tool name contains 'create' and description states 'Create a new tag in Airbyte.' Tags are metadata labels used for organization and filtering, not data-bearing resources.
Attacks that exploit this kind of access
Create a new tag in Airbyte. It is categorised as a Write tool in the Airbyte MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Airbyte MCP server in PolicyLayer and add a rule for airbyte_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 Airbyte. Nothing to install.
airbyte_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 airbyte_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 airbyte_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.
airbyte_create_tag is provided by the Airbyte MCP server (trustxai/airbyte-mcp). 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 →