Returns suggested models for a tier. Auto-detects your client environment (Claude Code, Gemini CLI, OpenCode, etc.) and filters suggestions accordingly. Native clients (Claude Code, Gemini CLI, Codex) receive only their provider
AI agents call get_model_suggestions to retrieve information from Oracle Models without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a classification system to retrieve model suggestions based on task complexity and client environment. It performs information retrieval only, with no side effects such as creating resources, executing code, or modifying data. The auto-detection of client environment is a read operation that informs which results to return.
From the tool's definition Tool 'Returns suggested models' and 'filters suggestions' — purely retrieves and presents information without modifying any data or triggering external operations.
Attacks that exploit this kind of access
Returns suggested models for a tier. Auto-detects your client environment (Claude Code, Gemini CLI, OpenCode, etc.) and filters suggestions accordingly. Native clients (Claude Code, Gemini CLI, Codex) receive only their provider. It is categorised as a Read tool in the Oracle Models MCP Server, which means it retrieves data without modifying state.
Register the Oracle Models MCP server in PolicyLayer and add a rule for get_model_suggestions: 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 Oracle Models. Nothing to install.
get_model_suggestions 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_model_suggestions 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_model_suggestions. 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_model_suggestions is provided by the Oracle Models MCP server (vanppsa/oracle-models). 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 →