AI agents call airbyte_list_tags to retrieve information from Airbyte without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'airbyte_list_tags' clearly indicates a retrieval operation that lists existing tags in an Airbyte instance. This is a non-destructive query with no side effects. While the description is empty, the naming convention combined with the context of sibling tools (create_tag, delete_tag, get_*) and the server's stated support for 'tags' strongly indicates this is a read-only listing function.
From the tool's definition Tool name contains 'list' which is a read operation that retrieves/queries data. No write, execute, destructive or financial operations are implied.
Attacks that exploit this kind of access
airbyte_list_tags. It is categorised as a Read tool in the Airbyte MCP Server, which means it retrieves data without modifying state.
Register the Airbyte MCP server in PolicyLayer and add a rule for airbyte_list_tags: 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_list_tags is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the airbyte_list_tags 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_list_tags. 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_list_tags 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 →