AI agents call airbyte_list_sources 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 'list' verb in the tool name and absence of any side-effect descriptors indicate this tool retrieves or queries a collection of sources from the Airbyte instance without modifying any data. This is a standard Read operation with minimal blast radius—unauthorized access would only expose configuration details about data sources.
From the tool's definition Tool name is 'airbyte_list_sources' with 'list' indicating a retrieval operation. The sibling tools include create, delete, and cancel operations, establishing that list operations are read-only in this API pattern.
Attacks that exploit this kind of access
airbyte_list_sources. 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_sources: 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_sources 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_sources 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_sources. 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_sources 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 →