AI agents call list_interviews to retrieve information from MCP Ashby Connector without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters interview records from the Ashby ATS system but does not create, modify, delete, or execute any operations. It is a straightforward read operation that poses minimal risk—typical query misuse would only expose existing data rather than cause harm to the system or data integrity.
From the tool's definition Tool name 'list_interviews' with description 'List interviews with filtering' indicates a query/retrieval operation. The verb 'list' combined with 'filtering' capability describes data retrieval without modification or side effects.
Documented attack patterns abuse exactly the kind of access list_interviews gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Ashby Connector, and nothing reaches the server without passing your rules. This is the rule we recommend for list_interviews:
{
"version": "1",
"default": "deny",
"tools": {
"list_interviews": {}
}
}list_interviews is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List interviews with filtering. It is categorised as a Read tool in the MCP Ashby Connector MCP Server, which means it retrieves data without modifying state.
Register the MCP Ashby Connector MCP server in PolicyLayer and add a rule for list_interviews: 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 MCP Ashby Connector. Nothing to install.
list_interviews 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 list_interviews 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 list_interviews. 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.
list_interviews is provided by the MCP Ashby Connector MCP server (thnico/mcp-ashby). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Ashby Connector, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 MCP Ashby Connector tools catalogued and risk-classified — across an index of 43,000+ MCP servers.