AI agents use airbyte_update_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 updates (modifies) an existing tag's name in Airbyte. It is reversible—the tag name can be changed again to a previous value or corrected. It has no financial implications, does not execute arbitrary code, and does not delete data irreversibly. The blast radius is limited to tag metadata in the Airbyte workspace.
From the tool's definition Tool name 'airbyte_update_tag' and description 'Update an existing tag's name' indicate modification of an existing resource.
Attacks that exploit this kind of access
Update an existing tag's name. 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_update_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_update_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_update_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_update_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_update_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 →