Return the currently active model (provider + id) or None.
AI agents call get_active_model_tool to retrieve information from Interview Prep without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward read operation that queries and returns system configuration state without modifying, executing, or deleting anything. The blast radius of misuse is minimal—an attacker gains only knowledge of which AI model provider/version is active in the interview prep system, which does not enable data exfiltration, code execution, or destructive actions.
From the tool's definition Tool returns the currently active model configuration (provider + id) with no side effects. It purely retrieves state information via 'Return' language.
Attacks that exploit this kind of access
Return the currently active model (provider + id) or None. It is categorised as a Read tool in the Interview Prep MCP Server, which means it retrieves data without modifying state.
Register the Interview Prep MCP server in PolicyLayer and add a rule for get_active_model_tool: 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 Interview Prep. Nothing to install.
get_active_model_tool 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 get_active_model_tool 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 get_active_model_tool. 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.
get_active_model_tool is provided by the Interview Prep MCP server (shenmali/interview-mcp-first). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_active_model_tool is one line of Interview Prep's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →