AI agents call airbyte_list_source_definitions 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.
This tool retrieves source definitions from Airbyte—a reference data read operation with no side effects. No modification, execution, deletion, or financial impact occurs. The lack of a description is mitigated by the clear intent signaled by the verb 'list', which unambiguously indicates a Read action.
From the tool's definition Tool name 'airbyte_list_source_definitions' indicates a listing/enumeration operation. The 'list' verb is a classic Read operation that retrieves and returns data without modification.
Attacks that exploit this kind of access
airbyte_list_source_definitions. 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_source_definitions: 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_source_definitions 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_source_definitions 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_source_definitions. 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_source_definitions 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 →